{"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/attention-dropout/papers/36","list_of":"/method/attention-dropout","method":"Attention Dropout","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":36,"pages_in_order":109,"rows_per_page":100,"rows":[3501,3600],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/attention-dropout","prev":"/method/attention-dropout/papers/35","next":"/method/attention-dropout/papers/37","papers":[{"paper":null,"slug":"look-before-you-leap-problem-elaboration","title":"Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models","date":"2024-02-24","arxiv_id":"2402.15764","n_code_links":0,"syntology":null},{"paper":"/paper/multicontrievers-analysis-of-dense-retrieval","slug":"multicontrievers-analysis-of-dense-retrieval","title":"MultiContrievers: Analysis of Dense Retrieval Representations","date":"2024-02-24","arxiv_id":"2402.15925","n_code_links":1,"syntology":null},{"paper":null,"slug":"prp-propagating-universal-perturbations-to","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","date":"2024-02-24","arxiv_id":"2402.15911","n_code_links":0,"syntology":null},{"paper":"/paper/semeval-2024-task-8-weighted-layer-averaging","slug":"semeval-2024-task-8-weighted-layer-averaging","title":"SemEval-2024 Task 8: Weighted Layer Averaging RoBERTa for Black-Box Machine-Generated Text Detection","date":"2024-02-24","arxiv_id":"2402.15873","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-first-look-at-gpt-apps-landscape-and","title":"A First Look at GPT Apps: Landscape and Vulnerability","date":"2024-02-23","arxiv_id":"2402.15105","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-parameter-efficiency-in-fine-tuning","slug":"advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","date":"2024-02-23","arxiv_id":"2402.15179","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 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; 0 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":["mlwu22/red"],"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":["listed","official"]}}},{"paper":"/paper/attributionbench-how-hard-is-automatic","slug":"attributionbench-how-hard-is-automatic","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","date":"2024-02-23","arxiv_id":"2402.15089","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-encoder-exploiting-the-potential-of","title":"Dual Encoder: Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction","date":"2024-02-23","arxiv_id":"2402.15370","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-chatgpt-for","title":"Evaluating the Performance of ChatGPT for Spam Email Detection","date":"2024-02-23","arxiv_id":"2402.15537","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-large-language-models-for-domain","title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","date":"2024-02-23","arxiv_id":"2402.15061","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-llms-to-compose-meta-review-drafts","slug":"prompting-llms-to-compose-meta-review-drafts","title":"LLMs as Meta-Reviewers' Assistants: A Case Study","date":"2024-02-23","arxiv_id":"2402.15589","n_code_links":1,"syntology":null},{"paper":"/paper/the-good-and-the-bad-exploring-privacy-issues","slug":"the-good-and-the-bad-exploring-privacy-issues","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","date":"2024-02-23","arxiv_id":"2402.16893","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":["phycholosogy/rag-privacy"],"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":"towards-efficient-active-learning-in-nlp-via","title":"Towards Efficient Active Learning in NLP via Pretrained Representations","date":"2024-02-23","arxiv_id":"2402.15613","n_code_links":0,"syntology":null},{"paper":"/paper/2d-matryoshka-sentence-embeddings","slug":"2d-matryoshka-sentence-embeddings","title":"2D Matryoshka Sentence Embeddings","date":"2024-02-22","arxiv_id":"2402.14776","n_code_links":1,"syntology":null},{"paper":"/paper/annotation-and-classification-of-relevant","slug":"annotation-and-classification-of-relevant","title":"Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts","date":"2024-02-22","arxiv_id":"2402.14457","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-generalization-capability-of-text","title":"Assessing generalization capability of text ranking models in Polish","date":"2024-02-22","arxiv_id":"2402.14318","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-detect","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","date":"2024-02-22","arxiv_id":"2402.14268","n_code_links":0,"syntology":null},{"paper":null,"slug":"copilot-evaluation-harness-evaluating-llm","title":"Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming","date":"2024-02-22","arxiv_id":"2402.14261","n_code_links":0,"syntology":null},{"paper":"/paper/hint-before-solving-prompting-guiding-llms-to","slug":"hint-before-solving-prompting-guiding-llms-to","title":"Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge","date":"2024-02-22","arxiv_id":"2402.14310","n_code_links":1,"syntology":null},{"paper":"/paper/kocosa-korean-context-aware-sarcasm-detection","slug":"kocosa-korean-context-aware-sarcasm-detection","title":"KoCoSa: Korean Context-aware Sarcasm Detection Dataset","date":"2024-02-22","arxiv_id":"2402.14428","n_code_links":1,"syntology":null},{"paper":null,"slug":"roboscript-code-generation-for-free-form","title":"RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation","date":"2024-02-22","arxiv_id":"2402.14623","n_code_links":0,"syntology":null},{"paper":"/paper/tokenization-counts-the-impact-of","slug":"tokenization-counts-the-impact-of","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","date":"2024-02-22","arxiv_id":"2402.14903","n_code_links":1,"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":["aadityasingh/tokenizationcounts"],"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"]}}},{"paper":null,"slug":"towards-understanding-counseling","title":"Towards Understanding Counseling Conversations: Domain Knowledge and Large Language Models","date":"2024-02-22","arxiv_id":"2402.14200","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-bert-capabilities-from-high","title":"Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching","date":"2024-02-22","arxiv_id":"2402.14408","n_code_links":0,"syntology":null},{"paper":"/paper/activerag-revealing-the-treasures-of","slug":"activerag-revealing-the-treasures-of","title":"ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents","date":"2024-02-21","arxiv_id":"2402.13547","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-evaluation-of-large-language-models-in","title":"An Evaluation of Large Language Models in Bioinformatics Research","date":"2024-02-21","arxiv_id":"2402.13714","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-explainable-transformer-based-model-for","title":"An Explainable Transformer-based Model for Phishing Email Detection: A Large Language Model Approach","date":"2024-02-21","arxiv_id":"2402.13871","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-hate-speech-nlp-s-challenges-and","title":"Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language","date":"2024-02-21","arxiv_id":"2402.13818","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-efficient-transformers-really-save","title":"Do Efficient Transformers Really Save Computation?","date":"2024-02-21","arxiv_id":"2402.13934","n_code_links":0,"syntology":null},{"paper":null,"slug":"green-ai-a-preliminary-empirical-study-on","title":"Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures","date":"2024-02-21","arxiv_id":"2402.13640","n_code_links":0,"syntology":null},{"paper":null,"slug":"hallucinations-or-attention-misdirection-the","title":"Hallucinations or Attention Misdirection? The Path to Strategic Value Extraction in Business Using Large Language Models","date":"2024-02-21","arxiv_id":"2402.14002","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-understanding-from","slug":"improving-language-understanding-from","title":"Improving Language Understanding from Screenshots","date":"2024-02-21","arxiv_id":"2402.14073","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":["princeton-nlp/ptp"],"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":"knowledge-graph-enhanced-large-language-model","title":"Knowledge Graph Enhanced Large Language Model Editing","date":"2024-02-21","arxiv_id":"2402.13593","n_code_links":0,"syntology":null},{"paper":"/paper/llm-jailbreak-attack-versus-defense","slug":"llm-jailbreak-attack-versus-defense","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","date":"2024-02-21","arxiv_id":"2402.13457","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":["ltroin/llm_attack_defense_arena"],"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/synfac-edit-synthetic-imitation-edit-feedback","slug":"synfac-edit-synthetic-imitation-edit-feedback","title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","date":"2024-02-21","arxiv_id":"2402.13919","n_code_links":1,"syntology":null},{"paper":"/paper/are-electra-s-sentence-embeddings-beyond","slug":"are-electra-s-sentence-embeddings-beyond","title":"Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity","date":"2024-02-20","arxiv_id":"2402.13130","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-retrieval-augmented-generation","slug":"benchmarking-retrieval-augmented-generation","title":"Benchmarking Retrieval-Augmented Generation for Medicine","date":"2024-02-20","arxiv_id":"2402.13178","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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":["teddy-xionggz/medrag","teddy-xionggz/mirage"],"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/can-gnn-be-good-adapter-for-llms","slug":"can-gnn-be-good-adapter-for-llms","title":"Can GNN be Good Adapter for LLMs?","date":"2024-02-20","arxiv_id":"2402.12984","n_code_links":2,"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":["zjunet/graphadapter","hxttkl/GraphAdapter"],"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/chatel-entity-linking-with-chatbots","slug":"chatel-entity-linking-with-chatbots","title":"ChatEL: Entity Linking with Chatbots","date":"2024-02-20","arxiv_id":"2402.14858","n_code_links":1,"syntology":null},{"paper":null,"slug":"evograd-a-dynamic-take-on-the-winograd-schema","title":"EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries","date":"2024-02-20","arxiv_id":"2402.13372","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-impact-of-table-to-text-methods","title":"Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data","date":"2024-02-20","arxiv_id":"2402.12869","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-the-system-message-really-important-to","title":"Is the System Message Really Important to Jailbreaks in Large Language Models?","date":"2024-02-20","arxiv_id":"2402.14857","n_code_links":0,"syntology":null},{"paper":"/paper/moelora-contrastive-learning-guided-mixture","slug":"moelora-contrastive-learning-guided-mixture","title":"MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models","date":"2024-02-20","arxiv_id":"2402.12851","n_code_links":1,"syntology":null},{"paper":null,"slug":"nl2formula-generating-spreadsheet-formulas","title":"NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries","date":"2024-02-20","arxiv_id":"2402.14853","n_code_links":0,"syntology":null},{"paper":"/paper/promptkd-distilling-student-friendly","slug":"promptkd-distilling-student-friendly","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","date":"2024-02-20","arxiv_id":"2402.12842","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["gmkim-ai/promptkd"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/reflect-rl-two-player-online-rl-fine-tuning","slug":"reflect-rl-two-player-online-rl-fine-tuning","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","date":"2024-02-20","arxiv_id":"2402.12621","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":1,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhourunlong/reflect-rl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sql-craft-text-to-sql-through-interactive","title":"$R^3$: \"This is My SQL, Are You With Me?\" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks","date":"2024-02-20","arxiv_id":"2402.14851","n_code_links":0,"syntology":null},{"paper":"/paper/the-impact-of-demonstrations-on-multilingual","slug":"the-impact-of-demonstrations-on-multilingual","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","date":"2024-02-20","arxiv_id":"2402.12976","n_code_links":1,"syntology":null},{"paper":"/paper/umbclu-at-semeval-2024-task-1a-and-1c","slug":"umbclu-at-semeval-2024-task-1a-and-1c","title":"UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation","date":"2024-02-20","arxiv_id":"2402.12730","n_code_links":1,"syntology":null},{"paper":"/paper/a-critical-evaluation-of-ai-feedback-for","slug":"a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","arxiv_id":"2402.12366","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":8,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["architsharma97/dpo-rlaif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-synthetic-data-approach-for-domain","title":"A synthetic data approach for domain generalization of NLI models","date":"2024-02-19","arxiv_id":"2402.12368","n_code_links":0,"syntology":null},{"paper":"/paper/acquiring-clean-language-models-from-backdoor","slug":"acquiring-clean-language-models-from-backdoor","title":"Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space","date":"2024-02-19","arxiv_id":"2402.12026","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":["zrw00/musclelora"],"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/analobench-benchmarking-the-identification-of","slug":"analobench-benchmarking-the-identification-of","title":"AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies","date":"2024-02-19","arxiv_id":"2402.12370","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"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) · 2 unverified","official":{"repos":["jhu-clsp/analogical-reasoning","JHU-CLSP/AnaloBench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ask-optimal-questions-aligning-large-language","title":"Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversational Search","date":"2024-02-19","arxiv_id":"2402.11827","n_code_links":0,"syntology":null},{"paper":"/paper/codeart-better-code-models-by-attention","slug":"codeart-better-code-models-by-attention","title":"CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking","date":"2024-02-19","arxiv_id":"2402.11842","n_code_links":1,"syntology":null},{"paper":null,"slug":"deepcode-ai-fix-fixing-security","title":"DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models","date":"2024-02-19","arxiv_id":"2402.13291","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-multilingual-fact-checking-at","title":"Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models","date":"2024-02-19","arxiv_id":"2402.12147","n_code_links":0,"syntology":null},{"paper":null,"slug":"feb4rag-evaluating-federated-search-in-the","title":"FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation","date":"2024-02-19","arxiv_id":"2402.11891","n_code_links":0,"syntology":null},{"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/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":"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":null,"slug":"key-ingredients-for-effective-zero-shot-cross","title":"Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks","date":"2024-02-19","arxiv_id":"2402.12279","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":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":"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/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":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":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":"/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":"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":"/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":"/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":"/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":"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":"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":"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":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/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":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":"/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/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":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/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":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":"/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":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":"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}],"record_sha256":"bc0dbe0ec5becf91f5c9e95cea7ec7174a5d63ca6926ce998dce367c4d926701","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}