{"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/cosine-annealing/papers/23","list_of":"/method/cosine-annealing","method":"Cosine Annealing","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":23,"pages_in_order":40,"rows_per_page":100,"rows":[2201,2300],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/22","next":"/method/cosine-annealing/papers/24","papers":[{"paper":"/paper/chatgpt-mt-competitive-for-high-but-not-low","slug":"chatgpt-mt-competitive-for-high-but-not-low","title":"ChatGPT MT: Competitive for High- (but not Low-) Resource Languages","date":"2023-09-14","arxiv_id":"2309.07423","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":["cmu-llab/gpt_mt_benchmark"],"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":null,"slug":"two-timin-repairing-smart-contracts-with-a","title":"Two Timin': Repairing Smart Contracts With A Two-Layered Approach","date":"2023-09-14","arxiv_id":"2309.07841","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-can-infer-psychological","title":"Large Language Models Can Infer Psychological Dispositions of Social Media Users","date":"2023-09-13","arxiv_id":"2309.08631","n_code_links":0,"syntology":null},{"paper":"/paper/traveling-words-a-geometric-interpretation-of","slug":"traveling-words-a-geometric-interpretation-of","title":"Traveling Words: A Geometric Interpretation of Transformers","date":"2023-09-13","arxiv_id":"2309.07315","n_code_links":1,"syntology":null},{"paper":"/paper/2309-05973","slug":"2309-05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","date":"2023-09-12","arxiv_id":"2309.05973","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["xanderdavies/circuit-breaking"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2309-06112","title":"Characterizing Latent Perspectives of Media Houses Towards Public Figures","date":"2023-09-12","arxiv_id":"2309.06112","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-llama-2-and-gpt-3-llms-for-hpc","title":"Comparing Llama-2 and GPT-3 LLMs for HPC kernels generation","date":"2023-09-12","arxiv_id":"2309.07103","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-ontology","slug":"exploring-large-language-models-for-ontology","title":"Exploring Large Language Models for Ontology Alignment","date":"2023-09-12","arxiv_id":"2309.07172","n_code_links":1,"syntology":null},{"paper":null,"slug":"strategic-behavior-of-large-language-models","title":"Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing","date":"2023-09-12","arxiv_id":"2309.05898","n_code_links":0,"syntology":null},{"paper":"/paper/the-moral-machine-experiment-on-large","slug":"the-moral-machine-experiment-on-large","title":"The Moral Machine Experiment on Large Language Models","date":"2023-09-12","arxiv_id":"2309.05958","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-the-potential-of-large-language","title":"Unveiling the potential of large language models in generating semantic and cross-language clones","date":"2023-09-12","arxiv_id":"2309.06424","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-analysis-gpts-across-time-in-legal","title":"Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task","date":"2023-09-11","arxiv_id":"2309.05501","n_code_links":0,"syntology":null},{"paper":"/paper/memory-injections-correcting-multi-hop","slug":"memory-injections-correcting-multi-hop","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","date":"2023-09-11","arxiv_id":"2309.05605","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["msakarvadia/memory_injections"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/sparseswin-swin-transformer-with-sparse","slug":"sparseswin-swin-transformer-with-sparse","title":"SparseSwin: Swin Transformer with Sparse Transformer Block","date":"2023-09-11","arxiv_id":"2309.05224","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-learning-with-minimum-instruction","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","date":"2023-09-11","arxiv_id":"2309.05475","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-learning-principles-with-a","title":"Implementing Learning Principles with a Personal AI Tutor: A Case Study","date":"2023-09-10","arxiv_id":"2309.13060","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-identify-distinguish-and","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","date":"2023-09-08","arxiv_id":"2309.04635","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-prompt-tuning-for-vision","title":"Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment","date":"2023-09-08","arxiv_id":"2309.04158","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-as-a-recommender-system-a","slug":"evaluating-chatgpt-as-a-recommender-system-a","title":"Evaluating ChatGPT as a Recommender System: A Rigorous Approach","date":"2023-09-07","arxiv_id":"2309.03613","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-supervised","slug":"evaluating-the-efficacy-of-supervised","title":"Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media","date":"2023-09-07","arxiv_id":"2309.03564","n_code_links":2,"syntology":null},{"paper":null,"slug":"flm-101b-an-open-llm-and-how-to-train-it-with","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","date":"2023-09-07","arxiv_id":"2309.03852","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-audio-captioning-via-audibility","slug":"zero-shot-audio-captioning-via-audibility","title":"Zero-Shot Audio Captioning via Audibility Guidance","date":"2023-09-07","arxiv_id":"2309.03884","n_code_links":0,"syntology":null},{"paper":"/paper/hae-rae-bench-evaluation-of-korean-knowledge","slug":"hae-rae-bench-evaluation-of-korean-knowledge","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","date":"2023-09-06","arxiv_id":"2309.02706","n_code_links":1,"syntology":null},{"paper":"/paper/codeapex-a-bilingual-programming-evaluation","slug":"codeapex-a-bilingual-programming-evaluation","title":"CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models","date":"2023-09-05","arxiv_id":"2309.01940","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-you-trust-chatgpt-perceived-credibility-of","title":"Do You Trust ChatGPT? -- Perceived Credibility of Human and AI-Generated Content","date":"2023-09-05","arxiv_id":"2309.02524","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-androids-dream-of-fictional-references-a","title":"Do androids dream of fictional references? A bibliographic dialogue with ChatGPT3.5","date":"2023-09-04","arxiv_id":"2312.00789","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-or-fine-tuning-a-comparative-study","slug":"prompting-or-fine-tuning-a-comparative-study","title":"Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction","date":"2023-09-04","arxiv_id":"2309.01715","n_code_links":1,"syntology":null},{"paper":"/paper/saturn-an-optimized-data-system-for-large","slug":"saturn-an-optimized-data-system-for-large","title":"Saturn: An Optimized Data System for Large Model Deep Learning Workloads","date":"2023-09-03","arxiv_id":"2309.01226","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-semantic-monitoring","title":"Large Language Models for Semantic Monitoring of Corporate Disclosures: A Case Study on Korea's Top 50 KOSPI Companies","date":"2023-09-01","arxiv_id":"2309.00208","n_code_links":0,"syntology":null},{"paper":"/paper/publicly-shareable-clinical-large-language","slug":"publicly-shareable-clinical-large-language","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","date":"2023-09-01","arxiv_id":"2309.00237","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":["starmpcc/asclepius"],"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/taken-out-of-context-on-measuring-situational","slug":"taken-out-of-context-on-measuring-situational","title":"Taken out of context: On measuring situational awareness in LLMs","date":"2023-09-01","arxiv_id":"2309.00667","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["asacooperstickland/situational-awareness-evals"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"why-do-universal-adversarial-attacks-work-on","title":"Why do universal adversarial attacks work on large language models?: Geometry might be the answer","date":"2023-09-01","arxiv_id":"2309.00254","n_code_links":0,"syntology":null},{"paper":"/paper/biocoder-a-benchmark-for-bioinformatics-code","slug":"biocoder-a-benchmark-for-bioinformatics-code","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","date":"2023-08-31","arxiv_id":"2308.16458","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":["gersteinlab/biocoder"],"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":"gpt-has-become-financially-literate-insights","title":"GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice","date":"2023-08-31","arxiv_id":"2309.00649","n_code_links":0,"syntology":null},{"paper":null,"slug":"ladder-of-thought-using-knowledge-as-steps-to","title":"Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection","date":"2023-08-31","arxiv_id":"2308.16763","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarathi-efficient-llm-inference-by","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","date":"2023-08-31","arxiv_id":"2308.16369","n_code_links":0,"syntology":null},{"paper":null,"slug":"jais-and-jais-chat-arabic-centric-foundation","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","date":"2023-08-30","arxiv_id":"2308.16149","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-data-preprocessors","title":"Large Language Models as Data Preprocessors","date":"2023-08-30","arxiv_id":"2308.16361","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-uncertainty-in-answers-from-any","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","date":"2023-08-30","arxiv_id":"2308.16175","n_code_links":0,"syntology":null},{"paper":"/paper/response-emergent-analogical-reasoning-in","slug":"response-emergent-analogical-reasoning-in","title":"Response: Emergent analogical reasoning in large language models","date":"2023-08-30","arxiv_id":"2308.16118","n_code_links":1,"syntology":null},{"paper":null,"slug":"furchat-an-embodied-conversational-agent","title":"FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions","date":"2023-08-29","arxiv_id":"2308.15214","n_code_links":0,"syntology":null},{"paper":"/paper/multi-party-goal-tracking-with-llms-comparing","slug":"multi-party-goal-tracking-with-llms-comparing","title":"Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering","date":"2023-08-29","arxiv_id":"2308.15231","n_code_links":1,"syntology":null},{"paper":null,"slug":"breaking-the-bank-with-chatgpt-few-shot-text","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","date":"2023-08-28","arxiv_id":"2308.14634","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-effects-in-large-language-models","slug":"cognitive-effects-in-large-language-models","title":"Cognitive Effects in Large Language Models","date":"2023-08-28","arxiv_id":"2308.14337","n_code_links":1,"syntology":null},{"paper":"/paper/distilled-gpt-for-source-code-summarization","slug":"distilled-gpt-for-source-code-summarization","title":"Distilled GPT for Source Code Summarization","date":"2023-08-28","arxiv_id":"2308.14731","n_code_links":1,"syntology":null},{"paper":null,"slug":"target-independent-xla-optimization-using","title":"Target-independent XLA optimization using Reinforcement Learning","date":"2023-08-28","arxiv_id":"2308.14364","n_code_links":0,"syntology":null},{"paper":"/paper/textrolspeech-a-text-style-control-speech","slug":"textrolspeech-a-text-style-control-speech","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","date":"2023-08-28","arxiv_id":"2308.14430","n_code_links":1,"syntology":null},{"paper":"/paper/examining-user-friendly-and-open-sourced","slug":"examining-user-friendly-and-open-sourced","title":"Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models","date":"2023-08-27","arxiv_id":"2308.14149","n_code_links":1,"syntology":null},{"paper":"/paper/a-wide-evaluation-of-chatgpt-on-affective","slug":"a-wide-evaluation-of-chatgpt-on-affective","title":"A Wide Evaluation of ChatGPT on Affective Computing Tasks","date":"2023-08-26","arxiv_id":"2308.13911","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","n_code_links":0,"syntology":null},{"paper":"/paper/cultural-alignment-in-large-language-models","slug":"cultural-alignment-in-large-language-models","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","date":"2023-08-25","arxiv_id":"2309.12342","n_code_links":1,"syntology":null},{"paper":"/paper/mllm-dataengine-an-iterative-refinement","slug":"mllm-dataengine-an-iterative-refinement","title":"MLLM-DataEngine: An Iterative Refinement Approach for MLLM","date":"2023-08-25","arxiv_id":"2308.13566","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opendatalab/mllm-dataengine"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transforming-the-output-of-generative-pre","title":"Transforming the Output of Generative Pre-trained Transformer: The Influence of the PGI Framework on Attention Dynamics","date":"2023-08-25","arxiv_id":"2308.13317","n_code_links":0,"syntology":null},{"paper":null,"slug":"financial-news-analytics-using-fine-tuned","title":"Financial News Analytics Using Fine-Tuned Llama 2 GPT Model","date":"2023-08-24","arxiv_id":"2308.13032","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-large-language-models-on-graphs","slug":"evaluating-large-language-models-on-graphs","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","date":"2023-08-22","arxiv_id":"2308.11224","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["ayame1006/llmtograph"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-effectiveness-of-gpt-models-in","title":"Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test","date":"2023-08-22","arxiv_id":"2308.11827","n_code_links":0,"syntology":null},{"paper":"/paper/mulmarker-a-gpt-assisted-comprehensive","slug":"mulmarker-a-gpt-assisted-comprehensive","title":"MulMarker: a comprehensive framework for identifying multi-gene prognostic signatures","date":"2023-08-22","arxiv_id":"2308.11349","n_code_links":1,"syntology":null},{"paper":null,"slug":"tryage-real-time-intelligent-routing-of-user","title":"Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models","date":"2023-08-22","arxiv_id":"2308.11601","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-in-the-loop-adaptive-decision-making-for","title":"GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems","date":"2023-08-21","arxiv_id":"2308.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradientcoin-a-peer-to-peer-decentralized","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","date":"2023-08-21","arxiv_id":"2308.10502","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-model-as-a-user-simulator","slug":"large-language-model-as-a-user-simulator","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","date":"2023-08-21","arxiv_id":"2308.11534","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"0 ran · 2 unverified","official":null}},{"paper":"/paper/large-language-models-on-wikipedia-style","slug":"large-language-models-on-wikipedia-style","title":"Large Language Models on Wikipedia-Style Survey Generation: an Evaluation in NLP Concepts","date":"2023-08-21","arxiv_id":"2308.10410","n_code_links":1,"syntology":null},{"paper":"/paper/activation-addition-steering-language-models","slug":"activation-addition-steering-language-models","title":"Steering Language Models With Activation Engineering","date":"2023-08-20","arxiv_id":"2308.10248","n_code_links":2,"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":["montemac/activation_additions"],"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/how-good-are-large-language-models-at-out-of","slug":"how-good-are-large-language-models-at-out-of","title":"How Good Are LLMs at Out-of-Distribution Detection?","date":"2023-08-20","arxiv_id":"2308.10261","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":["awenbocc/llm-ood"],"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/data-to-text-generation-for-severely-under","slug":"data-to-text-generation-for-severely-under","title":"Data-to-text Generation for Severely Under-Resourced Languages with GPT-3.5: A Bit of Help Needed from Google Translate","date":"2023-08-19","arxiv_id":"2308.09957","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-tailored-handwritten-text-recognition","title":"A tailored Handwritten-Text-Recognition System for Medieval Latin","date":"2023-08-18","arxiv_id":"2308.09368","n_code_links":0,"syntology":null},{"paper":"/paper/how-susceptible-are-llms-to-logical-fallacies","slug":"how-susceptible-are-llms-to-logical-fallacies","title":"How susceptible are LLMs to Logical Fallacies?","date":"2023-08-18","arxiv_id":"2308.09853","n_code_links":1,"syntology":null},{"paper":"/paper/wizardmath-empowering-mathematical-reasoning","slug":"wizardmath-empowering-mathematical-reasoning","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","date":"2023-08-18","arxiv_id":"2308.09583","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":8,"n_instrument":2,"unverified":6,"pointer_only":16,"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) · 6 unverified","official":null}},{"paper":null,"slug":"automatic-signboard-recognition-in-low","title":"Automatic Signboard Recognition in Low Quality Night Images","date":"2023-08-17","arxiv_id":"2308.08941","n_code_links":0,"syntology":null},{"paper":"/paper/beam-retrieval-general-end-to-end-retrieval","slug":"beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","arxiv_id":"2308.08973","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Alab-NII/2wikimultihop","canghongjian/beam_retriever"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/evaluation-of-really-good-grammatical-error","slug":"evaluation-of-really-good-grammatical-error","title":"Evaluation of really good grammatical error correction","date":"2023-08-17","arxiv_id":"2308.08982","n_code_links":1,"syntology":null},{"paper":null,"slug":"mascqa-a-question-answering-dataset-for","title":"MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models","date":"2023-08-17","arxiv_id":"2308.09115","n_code_links":0,"syntology":null},{"paper":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":8,"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":["wyl-willing/MindMap"],"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":null,"slug":"a-preliminary-study-on-a-conceptual-game","title":"A Preliminary Study on a Conceptual Game Feature Generation and Recommendation System","date":"2023-08-16","arxiv_id":"2308.13538","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-deception-reverse-penetrating-the","title":"Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models","date":"2023-08-16","arxiv_id":"2308.11521","n_code_links":0,"syntology":null},{"paper":null,"slug":"backward-reasoning-in-large-language-models","title":"Forward-Backward Reasoning in Large Language Models for Mathematical Verification","date":"2023-08-15","arxiv_id":"2308.07758","n_code_links":0,"syntology":null},{"paper":null,"slug":"calypso-llms-as-dungeon-masters-assistants","title":"CALYPSO: LLMs as Dungeon Masters' Assistants","date":"2023-08-15","arxiv_id":"2308.07540","n_code_links":0,"syntology":null},{"paper":"/paper/from-commit-message-generation-to-history","slug":"from-commit-message-generation-to-history","title":"From Commit Message Generation to History-Aware Commit Message Completion","date":"2023-08-15","arxiv_id":"2308.07655","n_code_links":1,"syntology":null},{"paper":null,"slug":"seer-super-optimization-explorer-for-hls","title":"SEER: Super-Optimization Explorer for HLS using E-graph Rewriting with MLIR","date":"2023-08-15","arxiv_id":"2308.07654","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximating-human-like-few-shot-learning","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","date":"2023-08-14","arxiv_id":"2308.06942","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-individual-trajectories-using-gpt","title":"Generating Individual Trajectories Using GPT-2 Trained from Scratch on Encoded Spatiotemporal Data","date":"2023-08-14","arxiv_id":"2308.07940","n_code_links":0,"syntology":null},{"paper":"/paper/llm-self-defense-by-self-examination-llms","slug":"llm-self-defense-by-self-examination-llms","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","date":"2023-08-14","arxiv_id":"2308.07308","n_code_links":1,"syntology":null},{"paper":null,"slug":"playing-with-words-comparing-the-vocabulary","title":"Playing with Words: Comparing the Vocabulary and Lexical Richness of ChatGPT and Humans","date":"2023-08-14","arxiv_id":"2308.07462","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-similarity-loss-for-neural-source","slug":"semantic-similarity-loss-for-neural-source","title":"Semantic Similarity Loss for Neural Source Code Summarization","date":"2023-08-14","arxiv_id":"2308.07429","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-student-errors-in-experimentation","title":"Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters","date":"2023-08-11","arxiv_id":"2308.06088","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-phenotype-recognition-in-clinical","slug":"enhancing-phenotype-recognition-in-clinical","title":"Enhancing Phenotype Recognition in Clinical Notes Using Large Language Models: PhenoBCBERT and PhenoGPT","date":"2023-08-11","arxiv_id":"2308.06294","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-in-cryptocurrency","title":"Large Language Models in Cryptocurrency Securities Cases: Can a GPT Model Meaningfully Assist Lawyers?","date":"2023-08-11","arxiv_id":"2308.06032","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-to-identify-social","slug":"large-language-models-to-identify-social","title":"Large Language Models to Identify Social Determinants of Health in Electronic Health Records","date":"2023-08-11","arxiv_id":"2308.06354","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":4,"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) · 2 unverified","official":{"repos":["aim-harvard/sdoh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptive-low-rank-adaptation-of-segment","slug":"adaptive-low-rank-adaptation-of-segment","title":"Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection","date":"2023-08-10","arxiv_id":"2308.05426","n_code_links":1,"syntology":null},{"paper":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","n_code_links":2,"syntology":{"ran":16,"of":27,"n_ran_checked":16,"n_instrument":0,"unverified":11,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/metacognitive-prompting-improves","slug":"metacognitive-prompting-improves","title":"Metacognitive Prompting Improves Understanding in Large Language Models","date":"2023-08-10","arxiv_id":"2308.05342","n_code_links":1,"syntology":null},{"paper":"/paper/rtllm-an-open-source-benchmark-for-design-rtl","slug":"rtllm-an-open-source-benchmark-for-design-rtl","title":"RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model","date":"2023-08-10","arxiv_id":"2308.05345","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":["hkust-zhiyao/rtllm"],"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":null,"slug":"testing-gpt-4-with-wolfram-alpha-and-code","title":"Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems","date":"2023-08-10","arxiv_id":"2308.05713","n_code_links":0,"syntology":null},{"paper":"/paper/weaverbird-empowering-financial-decision","slug":"weaverbird-empowering-financial-decision","title":"WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine","date":"2023-08-10","arxiv_id":"2308.05361","n_code_links":1,"syntology":null},{"paper":"/paper/you-only-prompt-once-on-the-capabilities-of","slug":"you-only-prompt-once-on-the-capabilities-of","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","date":"2023-08-10","arxiv_id":"2308.05596","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":["xinleihe/toxic-prompt"],"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":null,"slug":"an-empirical-study-on-using-large-language-1","title":"An Empirical Study on Using Large Language Models to Analyze Software Supply Chain Security Failures","date":"2023-08-09","arxiv_id":"2308.04898","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-e-empowering-e-commerce-authoring-with","title":"LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following","date":"2023-08-09","arxiv_id":"2308.04913","n_code_links":0,"syntology":null},{"paper":"/paper/llmebench-a-flexible-framework-for","slug":"llmebench-a-flexible-framework-for","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","date":"2023-08-09","arxiv_id":"2308.04945","n_code_links":1,"syntology":null},{"paper":"/paper/3d-vista-pre-trained-transformer-for-3d","slug":"3d-vista-pre-trained-transformer-for-3d","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","date":"2023-08-08","arxiv_id":"2308.04352","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"comparing-color-similarity-structures-between","title":"Gromov-Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models","date":"2023-08-08","arxiv_id":"2308.04381","n_code_links":0,"syntology":null}],"record_sha256":"e822069187dbcaa8c0b40cd3c47429c0659781d444d5d2423a3d88e38d8ff030","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}