{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/dense-connections/papers/ran/19","list_of":"/method/dense-connections","method":"Dense Connections","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":19,"pages_in_order":40,"rows_per_page":100,"rows":[1801,1900],"of":3929,"counts":{"archive_papers_tagged":29230,"with_a_code_link":12972,"where_syntology_ran_a_sample":3929,"not_listed_spam_title":0,"listed":29230,"listed_where_code_ran":3929,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3303,"every_run_a_failure_of_syntologys_instrument":626,"listed_with_a_run_with_no_instrument_failure":3303,"listed_every_run_a_failure_of_syntologys_instrument":626,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/dense-connections/papers/ran/1","prev":"/method/dense-connections/papers/ran/18","next":"/method/dense-connections/papers/ran/20","papers":[{"paper":"/paper/do-language-models-know-when-they-re","slug":"do-language-models-know-when-they-re","title":"Do Language Models Know When They're Hallucinating References?","date":"2023-05-29","arxiv_id":"2305.18248","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/hallucinated-references"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffusion-model-is-an-effective-planner-and-1","slug":"diffusion-model-is-an-effective-planner-and-1","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","date":"2023-05-29","arxiv_id":"2305.18459","n_code_links":1,"syntology":{"ran":19,"of":30,"n_ran_checked":18,"n_instrument":1,"unverified":11,"pointer_only":4,"phrase":"19 ran (of which 3 constructed an object rather than computing a result; 18 with no instrument failure: 5 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","official":{"repos":["tinnerhrhe/MTDiff"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/from-adversarial-arms-race-to-model-centric","slug":"from-adversarial-arms-race-to-model-centric","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","date":"2023-05-29","arxiv_id":"2305.18503","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp/robtest"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/generating-edu-extracts-for-plan-guided","slug":"generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","date":"2023-05-28","arxiv_id":"2305.17779","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":0,"n_instrument":6,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["griff4692/edu-sum"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/2305-18415","slug":"2305-18415","title":"Geometric Algebra Transformer","date":"2023-05-28","arxiv_id":"2305.18415","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qualcomm-ai-research/geometric-algebra-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/mitigating-label-biases-for-in-context","slug":"mitigating-label-biases-for-in-context","title":"Mitigating Label Biases for In-context Learning","date":"2023-05-28","arxiv_id":"2305.19148","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fywalter/label-bias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/kernel-ssl-kernel-kl-divergence-for-self","slug":"kernel-ssl-kernel-kl-divergence-for-self","title":"Matrix Information Theory for Self-Supervised Learning","date":"2023-05-27","arxiv_id":"2305.17326","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":1,"n_instrument":4,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yifanzhang-pro/matrix-llm","yifanzhang-pro/matrix-ssl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/is-centralized-training-with-decentralized","slug":"is-centralized-training-with-decentralized","title":"Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?","date":"2023-05-27","arxiv_id":"2305.17352","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zyh1999/cadp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dna-gpt-divergent-n-gram-analysis-for","slug":"dna-gpt-divergent-n-gram-analysis-for","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","date":"2023-05-27","arxiv_id":"2305.17359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xianjun-yang/dna-gpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/swiftsage-a-generative-agent-with-fast-and-1","slug":"swiftsage-a-generative-agent-with-fast-and-1","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","date":"2023-05-27","arxiv_id":"2305.17390","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/crossget-cross-guided-ensemble-of-tokens-for","slug":"crossget-cross-guided-ensemble-of-tokens-for","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","date":"2023-05-27","arxiv_id":"2305.17455","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sdc17/crossget"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-inductive-biases-in-transformers","slug":"graph-inductive-biases-in-transformers","title":"Graph Inductive Biases in Transformers without Message Passing","date":"2023-05-27","arxiv_id":"2305.17589","n_code_links":2,"syntology":{"ran":6,"of":12,"n_ran_checked":6,"n_instrument":0,"unverified":6,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["liamma/grit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zoeyyao27/graph-of-thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/future-conditioned-unsupervised-pretraining","slug":"future-conditioned-unsupervised-pretraining","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","date":"2023-05-26","arxiv_id":"2305.16683","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fffffarmer/pdt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/backpack-language-models","slug":"backpack-language-models","title":"Backpack Language Models","date":"2023-05-26","arxiv_id":"2305.16765","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/on-evaluating-adversarial-robustness-of-large","slug":"on-evaluating-adversarial-robustness-of-large","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","date":"2023-05-26","arxiv_id":"2305.16934","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yunqing-me/attackvlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffusionnag-task-guided-neural-architecture","slug":"diffusionnag-task-guided-neural-architecture","title":"DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models","date":"2023-05-26","arxiv_id":"2305.16943","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cownowan/diffusionnag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-imagine-visually-augmented","slug":"learning-to-imagine-visually-augmented","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","date":"2023-05-26","arxiv_id":"2305.16944","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/live"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/navgpt-explicit-reasoning-in-vision-and","slug":"navgpt-explicit-reasoning-in-vision-and","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","date":"2023-05-26","arxiv_id":"2305.16986","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gengzezhou/navgpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/biomedgpt-a-unified-and-generalist-biomedical","slug":"biomedgpt-a-unified-and-generalist-biomedical","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","date":"2023-05-26","arxiv_id":"2305.17100","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["taokz/biomedgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/comcat-towards-efficient-compression-and","slug":"comcat-towards-efficient-compression-and","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","date":"2023-05-26","arxiv_id":"2305.17235","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["jinqixiao/ComCAT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/chain-of-thought-hub-a-continuous-effort-to","slug":"chain-of-thought-hub-a-continuous-effort-to","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","date":"2023-05-26","arxiv_id":"2305.17306","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["franxyao/chain-of-thought-hub"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unitrec-a-unified-text-to-text-transformer","slug":"unitrec-a-unified-text-to-text-transformer","title":"UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation","date":"2023-05-25","arxiv_id":"2305.15756","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["veason-silverbullet/unitrec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-contradictory-hallucinations-of-large","slug":"self-contradictory-hallucinations-of-large","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","date":"2023-05-25","arxiv_id":"2305.15852","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["eth-sri/chatprotect"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/nextou-efficient-topology-aware-u-net-for","slug":"nextou-efficient-topology-aware-u-net-for","title":"NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation","date":"2023-05-25","arxiv_id":"2305.15911","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pengchengshi1220/nextou"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/generatect-text-guided-3d-chest-ct-generation","slug":"generatect-text-guided-3d-chest-ct-generation","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","date":"2023-05-25","arxiv_id":"2305.16037","n_code_links":1,"syntology":{"ran":14,"of":15,"n_ran_checked":13,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 4 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ibrahimethemhamamci/generatect"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/voyager-an-open-ended-embodied-agent-with","slug":"voyager-an-open-ended-embodied-agent-with","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","date":"2023-05-25","arxiv_id":"2305.16291","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["MineDojo/Voyager"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/landmark-attention-random-access-infinite","slug":"landmark-attention-random-access-infinite","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","date":"2023-05-25","arxiv_id":"2305.16300","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":5,"n_instrument":6,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["epfml/landmark-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}},{"paper":"/paper/on-the-tool-manipulation-capability-of-open","slug":"on-the-tool-manipulation-capability-of-open","title":"On the Tool Manipulation Capability of Open-source Large Language Models","date":"2023-05-25","arxiv_id":"2305.16504","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sambanova/toolbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-checker-plug-and-play-modules-for-fact","slug":"self-checker-plug-and-play-modules-for-fact","title":"Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models","date":"2023-05-24","arxiv_id":"2305.14623","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Miaoranmmm/SelfChecker"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/expertprompting-instructing-large-language","slug":"expertprompting-instructing-large-language","title":"ExpertPrompting: Instructing Large Language Models to be Distinguished Experts","date":"2023-05-24","arxiv_id":"2305.14688","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ofa-sys/expertllama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-causal-view-of-entity-bias-in-large","slug":"a-causal-view-of-entity-bias-in-large","title":"A Causal View of Entity Bias in (Large) Language Models","date":"2023-05-24","arxiv_id":"2305.14695","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luka-group/causal-view-of-entity-bias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/trusting-your-evidence-hallucinate-less-with","slug":"trusting-your-evidence-hallucinate-less-with","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","date":"2023-05-24","arxiv_id":"2305.14739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/from-words-to-wires-generating-functioning","slug":"from-words-to-wires-generating-functioning","title":"From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions","date":"2023-05-24","arxiv_id":"2305.14874","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cognitiveailab/words2wires"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/bytesized32-a-corpus-and-challenge-task-for","slug":"bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","date":"2023-05-24","arxiv_id":"2305.14879","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cognitiveailab/bytesized32"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-reliable-misinformation-mitigation","slug":"towards-reliable-misinformation-mitigation","title":"Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4","date":"2023-05-24","arxiv_id":"2305.14928","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["complexdata-mila/mitigatemisinfo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/editing-commonsense-knowledge-in-gpt","slug":"editing-commonsense-knowledge-in-gpt","title":"Editing Common Sense in Transformers","date":"2023-05-24","arxiv_id":"2305.14956","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["anshitag/memit_csk"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/tricking-llms-into-disobedience-understanding","slug":"tricking-llms-into-disobedience-understanding","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","date":"2023-05-24","arxiv_id":"2305.14965","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AetherPrior/TrickLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/reasoning-with-language-model-is-planning","slug":"reasoning-with-language-model-is-planning","title":"Reasoning with Language Model is Planning with World Model","date":"2023-05-24","arxiv_id":"2305.14992","n_code_links":3,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/how-to-distill-your-bert-an-empirical-study","slug":"how-to-distill-your-bert-an-empirical-study","title":"How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives","date":"2023-05-24","arxiv_id":"2305.15032","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["mainlp/how-to-distill-your-bert"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-optimization-of-large-language-model","slug":"prompt-optimization-of-large-language-model","title":"AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models","date":"2023-05-24","arxiv_id":"2305.15064","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["owaski/autoplan"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/inference-time-policy-adapters-ipa-tailoring","slug":"inference-time-policy-adapters-ipa-tailoring","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","date":"2023-05-24","arxiv_id":"2305.15065","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":5,"n_instrument":4,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gximinglu/ipa"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/have-llms-advanced-enough-a-challenging","slug":"have-llms-advanced-enough-a-challenging","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","date":"2023-05-24","arxiv_id":"2305.15074","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hgaurav2k/jeebench"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/huatuogpt-towards-taming-language-model-to-be","slug":"huatuogpt-towards-taming-language-model-to-be","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","date":"2023-05-24","arxiv_id":"2305.15075","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/huatuogpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/peek-across-improving-multi-document-modeling","slug":"peek-across-improving-multi-document-modeling","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","date":"2023-05-24","arxiv_id":"2305.15387","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":11,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["aviclu/peekacross"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/harnessing-the-power-of-large-language-models","slug":"harnessing-the-power-of-large-language-models","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","date":"2023-05-24","arxiv_id":"2305.15541","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gblackout/logicllama"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-is-all-you-need-learning-language","slug":"text-is-all-you-need-learning-language","title":"Text Is All You Need: Learning Language Representations for Sequential Recommendation","date":"2023-05-23","arxiv_id":"2305.13731","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/aligning-large-language-models-through","slug":"aligning-large-language-models-through","title":"Aligning Large Language Models through Synthetic Feedback","date":"2023-05-23","arxiv_id":"2305.13735","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["naver-ai/almost"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/condensing-multilingual-knowledge-with","slug":"condensing-multilingual-knowledge-with","title":"Condensing Multilingual Knowledge with Lightweight Language-Specific Modules","date":"2023-05-23","arxiv_id":"2305.13993","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["fe1ixxu/lms_fd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/patch-mix-contrastive-learning-with-audio","slug":"patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","arxiv_id":"2305.14032","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["raymin0223/patch-mix_contrastive_learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/weakly-supervised-3d-open-vocabulary-1","slug":"weakly-supervised-3d-open-vocabulary-1","title":"Weakly Supervised 3D Open-vocabulary Segmentation","date":"2023-05-23","arxiv_id":"2305.14093","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":10,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kunhao-liu/3d-ovs"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long","slug":"zeroscrolls-a-zero-shot-benchmark-for-long","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","date":"2023-05-23","arxiv_id":"2305.14196","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tau-nlp/zero_scrolls"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/factscore-fine-grained-atomic-evaluation-of","slug":"factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","arxiv_id":"2305.14251","n_code_links":4,"syntology":{"ran":11,"of":15,"n_ran_checked":10,"n_instrument":1,"unverified":4,"pointer_only":6,"phrase":"11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["shmsw25/factscore"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/wikichat-a-few-shot-llm-based-chatbot","slug":"wikichat-a-few-shot-llm-based-chatbot","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","date":"2023-05-23","arxiv_id":"2305.14292","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["stanford-oval/wikichat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","n_code_links":20,"syntology":{"ran":18,"of":26,"n_ran_checked":6,"n_instrument":12,"unverified":8,"pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"paper":"/paper/dynosaur-a-dynamic-growth-paradigm-for","slug":"dynosaur-a-dynamic-growth-paradigm-for","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","date":"2023-05-23","arxiv_id":"2305.14327","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":10,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["wadeyin9712/dynosaur"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/automatic-model-selection-with-large-language","slug":"automatic-model-selection-with-large-language","title":"Automatic Model Selection with Large Language Models for Reasoning","date":"2023-05-23","arxiv_id":"2305.14333","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xuzhao0/model-selection-reasoning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sophia-a-scalable-stochastic-second-order","slug":"sophia-a-scalable-stochastic-second-order","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","date":"2023-05-23","arxiv_id":"2305.14342","n_code_links":7,"syntology":{"ran":13,"of":19,"n_ran_checked":12,"n_instrument":1,"unverified":6,"pointer_only":0,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":null}},{"paper":"/paper/mathdial-a-dialogue-tutoring-dataset-with","slug":"mathdial-a-dialogue-tutoring-dataset-with","title":"MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems","date":"2023-05-23","arxiv_id":"2305.14536","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["eth-nlped/mathdial"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/all-roads-lead-to-rome-exploring-the","slug":"all-roads-lead-to-rome-exploring-the","title":"All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations","date":"2023-05-23","arxiv_id":"2305.14555","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["twinkle0331/bert-similarity"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rwkv-reinventing-rnns-for-the-transformer-era","slug":"rwkv-reinventing-rnns-for-the-transformer-era","title":"RWKV: Reinventing RNNs for the Transformer Era","date":"2023-05-22","arxiv_id":"2305.13048","n_code_links":14,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["BlinkDL/RWKV-LM","blinkdl/chatrwkv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/are-large-language-models-good-evaluators-for","slug":"are-large-language-models-good-evaluators-for","title":"Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization","date":"2023-05-22","arxiv_id":"2305.13091","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["damo-nlp-sg/llm_summeval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/gqa-training-generalized-multi-query","slug":"gqa-training-generalized-multi-query","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","date":"2023-05-22","arxiv_id":"2305.13245","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/recurrentgpt-interactive-generation-of","slug":"recurrentgpt-interactive-generation-of","title":"RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text","date":"2023-05-22","arxiv_id":"2305.13304","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aiwaves-cn/recurrentgpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/vdt-an-empirical-study-on-video-diffusion","slug":"vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","arxiv_id":"2305.13311","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":4,"n_instrument":4,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rerv/vdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/learning-subpocket-prototypes-for","slug":"learning-subpocket-prototypes-for","title":"Learning Subpocket Prototypes for Generalizable Structure-based Drug Design","date":"2023-05-22","arxiv_id":"2305.13997","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zaixizhang/flag"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/learning-joint-2d-3d-diffusion-models-for","slug":"learning-joint-2d-3d-diffusion-models-for","title":"Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation","date":"2023-05-21","arxiv_id":"2305.12347","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["graph-0/jodo"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/evaluating-the-performance-of-large-language","slug":"evaluating-the-performance-of-large-language","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","date":"2023-05-21","arxiv_id":"2305.12474","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openlmlab/gaokao-bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/theoremqa-a-theorem-driven-question-answering","slug":"theoremqa-a-theorem-driven-question-answering","title":"TheoremQA: A Theorem-driven Question Answering dataset","date":"2023-05-21","arxiv_id":"2305.12524","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":8,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wenhuchen/theoremqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/explaining-how-transformers-use-context-to","slug":"explaining-how-transformers-use-context-to","title":"Explaining How Transformers Use Context to Build Predictions","date":"2023-05-21","arxiv_id":"2305.12535","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":8,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mt-upc/logit-explanations"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/gene-set-summarization-using-large-language","slug":"gene-set-summarization-using-large-language","title":"Gene Set Summarization using Large Language Models","date":"2023-05-21","arxiv_id":"2305.13338","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["monarch-initiative/talisman"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/make-transformer-great-again-for-time-series","slug":"make-transformer-great-again-for-time-series","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","date":"2023-05-20","arxiv_id":"2305.12095","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wxie9/card"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-makes-for-good-visual-tokenizers-for","slug":"what-makes-for-good-visual-tokenizers-for","title":"What Makes for Good Visual Tokenizers for Large Language Models?","date":"2023-05-20","arxiv_id":"2305.12223","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tencentarc/gvt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/graph-propagation-transformer-for-graph","slug":"graph-propagation-transformer-for-graph","title":"Graph Propagation Transformer for Graph Representation Learning","date":"2023-05-19","arxiv_id":"2305.11424","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["czczup/gptrans"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/pointgpt-auto-regressively-generative-pre-1","slug":"pointgpt-auto-regressively-generative-pre-1","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","date":"2023-05-19","arxiv_id":"2305.11487","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CGuangyan-BIT/PointGPT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/diving-into-the-inter-consistency-of-large","slug":"diving-into-the-inter-consistency-of-large","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","date":"2023-05-19","arxiv_id":"2305.11595","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["waste-wood/ford"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/surgical-vqla-transformer-with-gated-vision","slug":"surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","arxiv_id":"2305.11692","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["longbai1006/surgical-vqla"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/clinical-camel-an-open-source-expert-level","slug":"clinical-camel-an-open-source-expert-level","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","date":"2023-05-19","arxiv_id":"2305.12031","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bowang-lab/clinical-camel"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalized-planning-in-pddl-domains-with","slug":"generalized-planning-in-pddl-domains-with","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","date":"2023-05-18","arxiv_id":"2305.11014","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tomsilver/llm-genplan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/evidence-of-meaning-in-language-models","slug":"evidence-of-meaning-in-language-models","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","date":"2023-05-18","arxiv_id":"2305.11169","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":0,"n_instrument":12,"unverified":1,"pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified","official":{"repos":["charlesjin/emergent-semantics"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/explaining-black-box-text-modules-in-natural","slug":"explaining-black-box-text-modules-in-natural","title":"Explaining black box text modules in natural language with language models","date":"2023-05-17","arxiv_id":"2305.09863","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csinva/imodelsX","microsoft/automated-explanations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficientsci-densely-connected-network-with-1","slug":"efficientsci-densely-connected-network-with-1","title":"EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imaging","date":"2023-05-17","arxiv_id":"2305.10006","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["ucaswangls/efficientsci"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ad-kd-attribution-driven-knowledge","slug":"ad-kd-attribution-driven-knowledge","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","date":"2023-05-17","arxiv_id":"2305.10010","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brucewsy/ad-kd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-data-augmentation-for-tabular-data","slug":"rethinking-data-augmentation-for-tabular-data","title":"Rethinking Data Augmentation for Tabular Data in Deep Learning","date":"2023-05-17","arxiv_id":"2305.10308","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["somaonishi/mtr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/tree-of-thoughts-deliberate-problem-solving-1","slug":"tree-of-thoughts-deliberate-problem-solving-1","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","date":"2023-05-17","arxiv_id":"2305.10601","n_code_links":6,"syntology":{"ran":19,"of":24,"n_ran_checked":18,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"19 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["princeton-nlp/tree-of-thought-llm","ysymyth/tree-of-thought-llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official"]}}},{"paper":"/paper/token-wise-decomposition-of-autoregressive","slug":"token-wise-decomposition-of-autoregressive","title":"Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions","date":"2023-05-17","arxiv_id":"2305.10614","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":7,"n_instrument":0,"unverified":5,"pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["byungdoh/llm_decomposition"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/instruction-tuned-models-are-quick-learners","slug":"instruction-tuned-models-are-quick-learners","title":"Instruction Tuned Models are Quick Learners","date":"2023-05-17","arxiv_id":"2306.05539","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["srsawant34/efficient_instruction_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/c-eval-a-multi-level-multi-discipline-chinese-1","slug":"c-eval-a-multi-level-multi-discipline-chinese-1","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","date":"2023-05-15","arxiv_id":"2305.08322","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hkust-nlp/ceval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-classification-via-large-language-models","slug":"text-classification-via-large-language-models","title":"Text Classification via Large Language Models","date":"2023-05-15","arxiv_id":"2305.08377","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shannonai/gpt-cls-carp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rl4f-generating-natural-language-feedback","slug":"rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","arxiv_id":"2305.08844","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feyzaakyurek/rl4f"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"paper":"/paper/small-models-are-valuable-plug-ins-for-large","slug":"small-models-are-valuable-plug-ins-for-large","title":"Small Models are Valuable Plug-ins for Large Language Models","date":"2023-05-15","arxiv_id":"2305.08848","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["JetRunner/SuperICL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-env-a-universal-platform-for-training","slug":"mobile-env-a-universal-platform-for-training","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","date":"2023-05-14","arxiv_id":"2305.08144","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":11,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opendfm/mobile-env-expe","x-lance/mobile-env"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/matsci-nlp-evaluating-scientific-language","slug":"matsci-nlp-evaluating-scientific-language","title":"MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling","date":"2023-05-14","arxiv_id":"2305.08264","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["banglab-udem-mila/nlp4matsci-acl23"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/investigating-emergent-goal-like-behaviour-in","slug":"investigating-emergent-goal-like-behaviour-in","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","date":"2023-05-13","arxiv_id":"2305.07970","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["phelps-sg/llm-cooperation","gitlab.com/sphelps/llm-cooperation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"29fcd01ad70cb85da667bd3089bf74b2c44b2d2da9651e34f6759fa619d3e915","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}