{"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/adam/papers/84","list_of":"/method/adam","method":"Adam","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":84,"pages_in_order":244,"rows_per_page":100,"rows":[8301,8400],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/83","next":"/method/adam/papers/85","papers":[{"paper":"/paper/fit-flexible-vision-transformer-for-diffusion","slug":"fit-flexible-vision-transformer-for-diffusion","title":"FiT: Flexible Vision Transformer for Diffusion Model","date":"2024-02-19","arxiv_id":"2402.12376","n_code_links":2,"syntology":{"ran":15,"of":17,"n_ran_checked":11,"n_instrument":4,"unverified":2,"pointer_only":3,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","official":{"repos":["whlzy/fit"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"graph-based-retriever-captures-the-long-tail","title":"Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge","date":"2024-02-19","arxiv_id":"2402.12352","n_code_links":0,"syntology":null},{"paper":"/paper/gtbench-uncovering-the-strategic-reasoning","slug":"gtbench-uncovering-the-strategic-reasoning","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","date":"2024-02-19","arxiv_id":"2402.12348","n_code_links":2,"syntology":null},{"paper":"/paper/head-wise-shareable-attention-for-large","slug":"head-wise-shareable-attention-for-large","title":"Head-wise Shareable Attention for Large Language Models","date":"2024-02-19","arxiv_id":"2402.11819","n_code_links":2,"syntology":null},{"paper":null,"slug":"imbue-improving-interpersonal-effectiveness","title":"IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction","date":"2024-02-19","arxiv_id":"2402.12556","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-open-source-there-yet-a-comparative-study","title":"Is Open-Source There Yet? A Comparative Study on Commercial and Open-Source LLMs in Their Ability to Label Chest X-Ray Reports","date":"2024-02-19","arxiv_id":"2402.12298","n_code_links":0,"syntology":null},{"paper":null,"slug":"karl-knowledge-aware-retrieval-and","title":"KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students","date":"2024-02-19","arxiv_id":"2402.12291","n_code_links":0,"syntology":null},{"paper":"/paper/language-model-adaptation-to-specialized","slug":"language-model-adaptation-to-specialized","title":"Language Model Adaptation to Specialized Domains through Selective Masking based on Genre and Topical Characteristics","date":"2024-02-19","arxiv_id":"2402.12036","n_code_links":1,"syntology":null},{"paper":"/paper/locality-sensitive-hashing-based-efficient","slug":"locality-sensitive-hashing-based-efficient","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","date":"2024-02-19","arxiv_id":"2402.12535","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":1,"n_instrument":11,"unverified":3,"pointer_only":0,"phrase":"12 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; 11 where Syntology's instrument failed) · 3 unverified","official":{"repos":["graph-com/hept"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mafin-enhancing-black-box-embeddings-with","title":"Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning","date":"2024-02-19","arxiv_id":"2402.12177","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-ranking-less-capable-language-models-are","title":"Enabling Weak LLMs to Judge Response Reliability via Meta Ranking","date":"2024-02-19","arxiv_id":"2402.12146","n_code_links":0,"syntology":null},{"paper":null,"slug":"mrke-the-multi-hop-reasoning-evaluation-of","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","date":"2024-02-19","arxiv_id":"2402.11924","n_code_links":0,"syntology":null},{"paper":null,"slug":"ontology-enhanced-claim-detection","title":"Ontology Enhanced Claim Detection","date":"2024-02-19","arxiv_id":"2402.12282","n_code_links":0,"syntology":null},{"paper":"/paper/perceiving-longer-sequences-with-bi","slug":"perceiving-longer-sequences-with-bi","title":"Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers","date":"2024-02-19","arxiv_id":"2402.12138","n_code_links":2,"syntology":{"ran":17,"of":28,"n_ran_checked":11,"n_instrument":6,"unverified":11,"pointer_only":27,"phrase":"17 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified","official":{"repos":["mrkshllr/bixt"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":10,"n_ran_no_instrument_failure":10,"n_unverified":11,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/query-based-adversarial-prompt-generation","slug":"query-based-adversarial-prompt-generation","title":"Query-Based Adversarial Prompt Generation","date":"2024-02-19","arxiv_id":"2402.12329","n_code_links":2,"syntology":null},{"paper":"/paper/robust-clip-unsupervised-adversarial-fine","slug":"robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","arxiv_id":"2402.12336","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":1,"n_instrument":6,"unverified":2,"pointer_only":0,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chs20/robustvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"shallow-synthesis-of-knowledge-in-gpt","title":"Shallow Synthesis of Knowledge in GPT-Generated Texts: A Case Study in Automatic Related Work Composition","date":"2024-02-19","arxiv_id":"2402.12255","n_code_links":0,"syntology":null},{"paper":null,"slug":"spml-a-dsl-for-defending-language-models","title":"SPML: A DSL for Defending Language Models Against Prompt Attacks","date":"2024-02-19","arxiv_id":"2402.11755","n_code_links":0,"syntology":null},{"paper":"/paper/standardize-aligning-language-models-with","slug":"standardize-aligning-language-models-with","title":"Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation","date":"2024-02-19","arxiv_id":"2402.12593","n_code_links":1,"syntology":null},{"paper":null,"slug":"stealing-the-invisible-unveiling-pre-trained","title":"Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels","date":"2024-02-19","arxiv_id":"2402.11953","n_code_links":0,"syntology":null},{"paper":null,"slug":"stick-to-your-role-stability-of-personal","title":"Stick to your Role! Stability of Personal Values Expressed in Large Language Models","date":"2024-02-19","arxiv_id":"2402.14846","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-joint-optimization-for-dnn","title":"CiMNet: Towards Joint Optimization for DNN Architecture and Configuration for Compute-In-Memory Hardware","date":"2024-02-19","arxiv_id":"2402.11780","n_code_links":0,"syntology":null},{"paper":"/paper/what-evidence-do-language-models-find","slug":"what-evidence-do-language-models-find","title":"What Evidence Do Language Models Find Convincing?","date":"2024-02-19","arxiv_id":"2402.11782","n_code_links":1,"syntology":{"ran":8,"of":14,"n_ran_checked":8,"n_instrument":0,"unverified":6,"pointer_only":0,"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) · 6 unverified","official":{"repos":["alexwan0/rag-convincingness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"your-large-language-model-is-secretly-a","title":"Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One","date":"2024-02-19","arxiv_id":"2402.12150","n_code_links":0,"syntology":null},{"paper":"/paper/a-curious-case-of-searching-for-the","slug":"a-curious-case-of-searching-for-the","title":"A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models","date":"2024-02-18","arxiv_id":"2402.11469","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-deception-detection-go-deeper-dataset","title":"Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning","date":"2024-02-18","arxiv_id":"2402.11432","n_code_links":0,"syntology":null},{"paper":"/paper/combinatorial-client-master-multiagent-deep","slug":"combinatorial-client-master-multiagent-deep","title":"Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing","date":"2024-02-18","arxiv_id":"2402.11653","n_code_links":2,"syntology":null},{"paper":null,"slug":"decoding-news-narratives-a-critical-analysis","title":"Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection","date":"2024-02-18","arxiv_id":"2402.11621","n_code_links":0,"syntology":null},{"paper":null,"slug":"dictllm-harnessing-key-value-data-structures","title":"DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics","date":"2024-02-18","arxiv_id":"2402.11481","n_code_links":0,"syntology":null},{"paper":"/paper/eventrl-enhancing-event-extraction-with","slug":"eventrl-enhancing-event-extraction-with","title":"EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models","date":"2024-02-18","arxiv_id":"2402.11430","n_code_links":1,"syntology":null},{"paper":"/paper/factpico-factuality-evaluation-for-plain","slug":"factpico-factuality-evaluation-for-plain","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","date":"2024-02-18","arxiv_id":"2402.11456","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":["lilywchen/factpico"],"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/gnnavi-navigating-the-information-flow-in","slug":"gnnavi-navigating-the-information-flow-in","title":"GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network","date":"2024-02-18","arxiv_id":"2402.11709","n_code_links":1,"syntology":null},{"paper":null,"slug":"kmmlu-measuring-massive-multitask-language","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","date":"2024-02-18","arxiv_id":"2402.11548","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-failure-integrating-negative","slug":"learning-from-failure-integrating-negative","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","date":"2024-02-18","arxiv_id":"2402.11651","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":4,"n_instrument":1,"unverified":1,"pointer_only":6,"phrase":"5 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["reason-wang/nat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/longagent-scaling-language-models-to-128k","slug":"longagent-scaling-language-models-to-128k","title":"LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration","date":"2024-02-18","arxiv_id":"2402.11550","n_code_links":1,"syntology":null},{"paper":"/paper/metric-learning-encoding-models-identify","slug":"metric-learning-encoding-models-identify","title":"Metric-Learning Encoding Models Identify Processing Profiles of Linguistic Features in BERT's Representations","date":"2024-02-18","arxiv_id":"2402.11608","n_code_links":1,"syntology":null},{"paper":null,"slug":"msynfd-multi-hop-syntax-aware-fake-news","title":"MSynFD: Multi-hop Syntax aware Fake News Detection","date":"2024-02-18","arxiv_id":"2402.14834","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-dimensional-evaluation-of-empathetic","title":"Multi-dimensional Evaluation of Empathetic Dialog Responses","date":"2024-02-18","arxiv_id":"2402.11409","n_code_links":0,"syntology":null},{"paper":"/paper/multi-task-inference-can-large-language","slug":"multi-task-inference-can-large-language","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","date":"2024-02-18","arxiv_id":"2402.11597","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":["guijinson/mti-bench"],"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/perils-of-self-feedback-self-bias-amplifies","slug":"perils-of-self-feedback-self-bias-amplifies","title":"Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement","date":"2024-02-18","arxiv_id":"2402.11436","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"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":["xu1998hz/llm_self_bias"],"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":null,"slug":"ploutos-towards-interpretable-stock-movement","title":"Ploutos: Towards interpretable stock movement prediction with financial large language model","date":"2024-02-18","arxiv_id":"2403.00782","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-zeroth-order-optimization-for","slug":"revisiting-zeroth-order-optimization-for","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","date":"2024-02-18","arxiv_id":"2402.11592","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":3,"n_instrument":6,"unverified":4,"pointer_only":13,"phrase":"9 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; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zo-bench/zo-llm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"utilizing-bert-for-information-retrieval","title":"Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges","date":"2024-02-18","arxiv_id":"2403.00784","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-flan-scaling-human-labeled-tasks-in","title":"Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning","date":"2024-02-18","arxiv_id":"2402.11690","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-of-thoughts-trial-and-error-problem","slug":"boosting-of-thoughts-trial-and-error-problem","title":"Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models","date":"2024-02-17","arxiv_id":"2402.11140","n_code_links":2,"syntology":null},{"paper":null,"slug":"detecting-a-proxy-for-potential-comorbid-adhd","title":"Detecting a Proxy for Potential Comorbid ADHD in People Reporting Anxiety Symptoms from Social Media Data","date":"2024-02-17","arxiv_id":"2403.05561","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-chatgpt-for-next-generation","title":"Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges","date":"2024-02-17","arxiv_id":"2402.11203","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendec-a-robust-generative-question","title":"GenDec: A robust generative Question-decomposition method for Multi-hop reasoning","date":"2024-02-17","arxiv_id":"2402.11166","n_code_links":0,"syntology":null},{"paper":null,"slug":"reasoning-before-comparison-llm-enhanced","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","date":"2024-02-17","arxiv_id":"2402.11398","n_code_links":0,"syntology":null},{"paper":"/paper/revit-enhancing-vision-transformers-with","slug":"revit-enhancing-vision-transformers-with","title":"ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections","date":"2024-02-17","arxiv_id":"2402.11301","n_code_links":1,"syntology":{"ran":22,"of":24,"n_ran_checked":20,"n_instrument":2,"unverified":2,"pointer_only":1,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["adiko1997/revit"],"state":"official (archive's flag): 22 ran","n_ran":22,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/zerog-investigating-cross-dataset-zero-shot","slug":"zerog-investigating-cross-dataset-zero-shot","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","date":"2024-02-17","arxiv_id":"2402.11235","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":["nineabyss/zerog"],"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":null,"slug":"assessing-the-reasoning-abilities-of-chatgpt","title":"Assessing the Reasoning Abilities of ChatGPT in the Context of Claim Verification","date":"2024-02-16","arxiv_id":"2402.10735","n_code_links":0,"syntology":null},{"paper":"/paper/can-llms-speak-for-diverse-people-tuning-llms","slug":"can-llms-speak-for-diverse-people-tuning-llms","title":"Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements","date":"2024-02-16","arxiv_id":"2402.10614","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":["tianyi-lab/debatune"],"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":null,"slug":"can-separators-improve-chain-of-thought","title":"Can Separators Improve Chain-of-Thought Prompting?","date":"2024-02-16","arxiv_id":"2402.10645","n_code_links":0,"syntology":null},{"paper":"/paper/contiformer-continuous-time-transformer-for-1","slug":"contiformer-continuous-time-transformer-for-1","title":"ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling","date":"2024-02-16","arxiv_id":"2402.10635","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":8,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["microsoft/SeqML"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/disordered-dabs-a-benchmark-for-dynamic","slug":"disordered-dabs-a-benchmark-for-dynamic","title":"Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts","date":"2024-02-16","arxiv_id":"2402.10554","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-patch-aware-enrichment-transformer","slug":"dynamic-patch-aware-enrichment-transformer","title":"Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification","date":"2024-02-16","arxiv_id":"2402.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"emoji-driven-crypto-assets-market-reactions","title":"Emoji Driven Crypto Assets Market Reactions","date":"2024-02-16","arxiv_id":"2402.10481","n_code_links":0,"syntology":null},{"paper":null,"slug":"fintral-a-family-of-gpt-4-level-multimodal","title":"FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models","date":"2024-02-16","arxiv_id":"2402.10986","n_code_links":0,"syntology":null},{"paper":"/paper/german-text-simplification-finetuning-large","slug":"german-text-simplification-finetuning-large","title":"German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data","date":"2024-02-16","arxiv_id":"2402.10675","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-reliable-are-automatic-evaluation-methods","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?","date":"2024-02-16","arxiv_id":"2402.10770","n_code_links":0,"syntology":null},{"paper":"/paper/in-search-of-needles-in-a-10m-haystack","slug":"in-search-of-needles-in-a-10m-haystack","title":"In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss","date":"2024-02-16","arxiv_id":"2402.10790","n_code_links":2,"syntology":null},{"paper":null,"slug":"inference-to-the-best-explanation-in-large","title":"Inference to the Best Explanation in Large Language Models","date":"2024-02-16","arxiv_id":"2402.10767","n_code_links":0,"syntology":null},{"paper":"/paper/jailbreaking-proprietary-large-language","slug":"jailbreaking-proprietary-large-language","title":"When \"Competency\" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers","date":"2024-02-16","arxiv_id":"2402.10601","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":4,"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) · 3 unverified","official":{"repos":["divijh/jailbreak_cryptography"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-as-zero-shot-dialogue","slug":"large-language-models-as-zero-shot-dialogue","title":"Large Language Models as Zero-shot Dialogue State Tracker through Function Calling","date":"2024-02-16","arxiv_id":"2402.10466","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["facebookresearch/fnctod"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"large-language-models-fall-short","title":"Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives","date":"2024-02-16","arxiv_id":"2402.11051","n_code_links":0,"syntology":null},{"paper":"/paper/linear-transformers-with-learnable-kernel","slug":"linear-transformers-with-learnable-kernel","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","date":"2024-02-16","arxiv_id":"2402.10644","n_code_links":2,"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":["sustcsonglin/flash-linear-attention","corl-team/rebased"],"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/linkner-linking-local-named-entity","slug":"linkner-linking-local-named-entity","title":"LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty","date":"2024-02-16","arxiv_id":"2402.10573","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-in-the-heart-of-differential-testing-a","title":"LLMs in the Heart of Differential Testing: A Case Study on a Medical Rule Engine","date":"2024-02-16","arxiv_id":"2404.03664","n_code_links":0,"syntology":null},{"paper":null,"slug":"logelectra-self-supervised-anomaly-detection","title":"LogELECTRA: Self-supervised Anomaly Detection for Unstructured Logs","date":"2024-02-16","arxiv_id":"2402.10397","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-cultural-commonsense-knowledge","title":"Cultural Commonsense Knowledge for Intercultural Dialogues","date":"2024-02-16","arxiv_id":"2402.10689","n_code_links":0,"syntology":null},{"paper":"/paper/network-formation-and-dynamics-among-multi","slug":"network-formation-and-dynamics-among-multi","title":"Network Formation and Dynamics Among Multi-LLMs","date":"2024-02-16","arxiv_id":"2402.10659","n_code_links":1,"syntology":null},{"paper":"/paper/toolsword-unveiling-safety-issues-of-large","slug":"toolsword-unveiling-safety-issues-of-large","title":"ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages","date":"2024-02-16","arxiv_id":"2402.10753","n_code_links":1,"syntology":null},{"paper":"/paper/universal-prompt-optimizer-for-safe-text-to","slug":"universal-prompt-optimizer-for-safe-text-to","title":"Universal Prompt Optimizer for Safe Text-to-Image Generation","date":"2024-02-16","arxiv_id":"2402.10882","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-llm-adaptation-for-question","slug":"unsupervised-llm-adaptation-for-question","title":"Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction","date":"2024-02-16","arxiv_id":"2402.12170","n_code_links":1,"syntology":null},{"paper":"/paper/weak-mamba-unet-visual-mamba-makes-cnn-and","slug":"weak-mamba-unet-visual-mamba-makes-cnn-and","title":"Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation","date":"2024-02-16","arxiv_id":"2402.10887","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ziyangwang007/mamba-unet"],"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":["listed","official"]}}},{"paper":"/paper/a-strongreject-for-empty-jailbreaks","slug":"a-strongreject-for-empty-jailbreaks","title":"A StrongREJECT for Empty Jailbreaks","date":"2024-02-15","arxiv_id":"2402.10260","n_code_links":2,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["alexandrasouly/strongreject"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"an-analysis-of-langauge-frequency-and-error","title":"An Analysis of Language Frequency and Error Correction for Esperanto","date":"2024-02-15","arxiv_id":"2402.09696","n_code_links":0,"syntology":null},{"paper":null,"slug":"best-arm-identification-for-prompt-learning","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","date":"2024-02-15","arxiv_id":"2402.09723","n_code_links":0,"syntology":null},{"paper":null,"slug":"camouflage-is-all-you-need-evaluating-and","title":"Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks","date":"2024-02-15","arxiv_id":"2402.09874","n_code_links":0,"syntology":null},{"paper":"/paper/covidhealth-a-benchmark-twitter-dataset-and","slug":"covidhealth-a-benchmark-twitter-dataset-and","title":"COVIDHealth: A Benchmark Twitter Dataset and Machine Learning based Web Application for Classifying COVID-19 Discussions","date":"2024-02-15","arxiv_id":"2402.09897","n_code_links":1,"syntology":null},{"paper":"/paper/data-engineering-for-scaling-language-models","slug":"data-engineering-for-scaling-language-models","title":"Data Engineering for Scaling Language Models to 128K Context","date":"2024-02-15","arxiv_id":"2402.10171","n_code_links":1,"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":["franxyao/long-context-data-engineering"],"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":null,"slug":"fine-tuning-large-language-model-llm","title":"Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4","date":"2024-02-15","arxiv_id":"2402.10083","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-s-assessment-of-its-performance-in-a","title":"GPT-4's assessment of its performance in a USMLE-based case study","date":"2024-02-15","arxiv_id":"2402.09654","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-language-model-with-chunking-free","title":"Grounding Language Model with Chunking-Free In-Context Retrieval","date":"2024-02-15","arxiv_id":"2402.09760","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-machine","title":"Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization","date":"2024-02-15","arxiv_id":"2402.09725","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-forecasting-and","title":"Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review","date":"2024-02-15","arxiv_id":"2402.10350","n_code_links":0,"syntology":null},{"paper":null,"slug":"nyctale-neuro-evidence-transformer-for","title":"NYCTALE: Neuro-Evidence Transformer for Adaptive and Personalized Lung Nodule Invasiveness Prediction","date":"2024-02-15","arxiv_id":"2402.10066","n_code_links":0,"syntology":null},{"paper":"/paper/openmathinstruct-1-a-1-8-million-math","slug":"openmathinstruct-1-a-1-8-million-math","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","date":"2024-02-15","arxiv_id":"2402.10176","n_code_links":1,"syntology":null},{"paper":"/paper/pal-proxy-guided-black-box-attack-on-large","slug":"pal-proxy-guided-black-box-attack-on-large","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","date":"2024-02-15","arxiv_id":"2402.09674","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-based-bias-calibration-for-better-zero","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","date":"2024-02-15","arxiv_id":"2402.10353","n_code_links":0,"syntology":null},{"paper":null,"slug":"protchatgpt-towards-understanding-proteins","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","date":"2024-02-15","arxiv_id":"2402.09649","n_code_links":0,"syntology":null},{"paper":"/paper/spike-driven-transformer-v2-meta-spiking","slug":"spike-driven-transformer-v2-meta-spiking","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","date":"2024-02-15","arxiv_id":"2404.03663","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["biclab/spike-driven-transformer-v2"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-butterfly-effect-of-model-editing-few","slug":"the-butterfly-effect-of-model-editing-few","title":"The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse","date":"2024-02-15","arxiv_id":"2402.09656","n_code_links":1,"syntology":null},{"paper":"/paper/unlocking-structure-measuring-introducing-pdd","slug":"unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","n_code_links":1,"syntology":null},{"paper":null,"slug":"x-lifecycle-learning-for-cloud-incident","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","date":"2024-02-15","arxiv_id":"2404.03662","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-language-model-for-particle-tracking","title":"A Language Model for Particle Tracking","date":"2024-02-14","arxiv_id":"2402.10239","n_code_links":0,"syntology":null},{"paper":"/paper/api-pack-a-massive-multilingual-dataset-for","slug":"api-pack-a-massive-multilingual-dataset-for","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","date":"2024-02-14","arxiv_id":"2402.09615","n_code_links":1,"syntology":null},{"paper":"/paper/aqa-bench-an-interactive-benchmark-for","slug":"aqa-bench-an-interactive-benchmark-for","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","date":"2024-02-14","arxiv_id":"2402.09404","n_code_links":1,"syntology":null},{"paper":"/paper/bidirectional-generative-pre-training-for","slug":"bidirectional-generative-pre-training-for","title":"Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning","date":"2024-02-14","arxiv_id":"2402.09558","n_code_links":1,"syntology":null}],"record_sha256":"ec439bfdfbd86b28def1a907b21b3d4bedf489fce65daba365e5d77d0292bc90","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}