{"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/37","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":37,"pages_in_order":109,"rows_per_page":100,"rows":[3601,3700],"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/36","next":"/method/attention-dropout/papers/38","papers":[{"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":"/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":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":null,"slug":"emerging-opportunities-of-using-large","title":"Emerging Opportunities of Using Large Language Models for Translation Between Drug Molecules and Indications","date":"2024-02-14","arxiv_id":"2402.09588","n_code_links":0,"syntology":null},{"paper":null,"slug":"fgeo-tp-a-language-model-enhanced-solver-for","title":"FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems","date":"2024-02-14","arxiv_id":"2402.09047","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-enhanced-1","title":"Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies","date":"2024-02-14","arxiv_id":"2402.09282","n_code_links":0,"syntology":null},{"paper":"/paper/mpirigen-mpi-code-generation-through-domain","slug":"mpirigen-mpi-code-generation-through-domain","title":"MPIrigen: MPI Code Generation through Domain-Specific Language Models","date":"2024-02-14","arxiv_id":"2402.09126","n_code_links":1,"syntology":null},{"paper":null,"slug":"regional-inflation-analysis-using-social","title":"Regional inflation analysis using social network data","date":"2024-02-14","arxiv_id":"2403.00774","n_code_links":0,"syntology":null},{"paper":null,"slug":"scamspot-fighting-financial-fraud-in","title":"ScamSpot: Fighting Financial Fraud in Instagram Comments","date":"2024-02-14","arxiv_id":"2402.08869","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-counterfactual-tasks-to-evaluate-the","title":"Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models","date":"2024-02-14","arxiv_id":"2402.08955","n_code_links":0,"syntology":null},{"paper":null,"slug":"auditing-counterfire-evaluating-advanced","title":"\"Reasoning\" with Rhetoric: On the Style-Evidence Tradeoff in LLM-Generated Counter-Arguments","date":"2024-02-13","arxiv_id":"2402.08498","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert4fca-a-method-for-bipartite-link","title":"BERT4FCA: A Method for Bipartite Link Prediction using Formal Concept Analysis and BERT","date":"2024-02-13","arxiv_id":"2402.08236","n_code_links":0,"syntology":null},{"paper":"/paper/cold-attack-jailbreaking-llms-with","slug":"cold-attack-jailbreaking-llms-with","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","date":"2024-02-13","arxiv_id":"2402.08679","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yu-fangxu/cold-attack"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"eliciting-big-five-personality-traits-in","title":"Eliciting Personality Traits in Large Language Models","date":"2024-02-13","arxiv_id":"2402.08341","n_code_links":0,"syntology":null},{"paper":"/paper/improving-black-box-robustness-with-in","slug":"improving-black-box-robustness-with-in","title":"Improving Black-box Robustness with In-Context Rewriting","date":"2024-02-13","arxiv_id":"2402.08225","n_code_links":1,"syntology":null},{"paper":null,"slug":"lying-blindly-bypassing-chatgpt-s-safeguards","title":"Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims","date":"2024-02-13","arxiv_id":"2402.08467","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-and-controlling-instruction-in","slug":"measuring-and-controlling-instruction-in","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","date":"2024-02-13","arxiv_id":"2402.10962","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":5,"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) · 3 unverified","official":{"repos":["likenneth/persona_drift"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mitigating-object-hallucination-in-large","title":"Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance","date":"2024-02-13","arxiv_id":"2402.08680","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-optimization-in-multi-step-tasks","slug":"prompt-optimization-in-multi-step-tasks","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","date":"2024-02-13","arxiv_id":"2402.08702","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"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":["yongchao98/promst"],"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":"/paper/addressing-cognitive-bias-in-medical-language","slug":"addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","arxiv_id":"2402.08113","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["carlwharris/cog-bias-med-llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/breakgpt-a-large-language-model-with-multi","slug":"breakgpt-a-large-language-model-with-multi","title":"BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection","date":"2024-02-12","arxiv_id":"2402.07536","n_code_links":1,"syntology":null},{"paper":"/paper/cybermetric-a-benchmark-dataset-for","slug":"cybermetric-a-benchmark-dataset-for","title":"CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge","date":"2024-02-12","arxiv_id":"2402.07688","n_code_links":1,"syntology":null},{"paper":null,"slug":"developing-a-multi-variate-prediction-model-1","title":"Developing a Multi-variate Prediction Model For COVID-19 From Crowd-sourced Respiratory Voice Data","date":"2024-02-12","arxiv_id":"2402.07619","n_code_links":0,"syntology":null},{"paper":"/paper/g-retriever-retrieval-augmented-generation","slug":"g-retriever-retrieval-augmented-generation","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","date":"2024-02-12","arxiv_id":"2402.07630","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xiaoxinhe/g-retriever"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"investigating-the-impact-of-data","title":"Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation","date":"2024-02-12","arxiv_id":"2402.08100","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-ai-to-advance-science-and","title":"Leveraging AI to Advance Science and Computing Education across Africa: Challenges, Progress and Opportunities","date":"2024-02-12","arxiv_id":"2402.07397","n_code_links":0,"syntology":null},{"paper":"/paper/poisonedrag-knowledge-poisoning-attacks-to","slug":"poisonedrag-knowledge-poisoning-attacks-to","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-02-12","arxiv_id":"2402.07867","n_code_links":2,"syntology":{"ran":12,"of":17,"n_ran_checked":11,"n_instrument":1,"unverified":5,"pointer_only":7,"phrase":"12 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["sleeepeer/poisonedrag"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"t-rag-lessons-from-the-llm-trenches","title":"T-RAG: Lessons from the LLM Trenches","date":"2024-02-12","arxiv_id":"2402.07483","n_code_links":0,"syntology":null},{"paper":"/paper/hyperbert-mixing-hypergraph-aware-layers-with","slug":"hyperbert-mixing-hypergraph-aware-layers-with","title":"HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs","date":"2024-02-11","arxiv_id":"2402.07309","n_code_links":1,"syntology":null},{"paper":null,"slug":"prompt-perturbation-in-retrieval-augmented","title":"Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models","date":"2024-02-11","arxiv_id":"2402.07179","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-ordering-in-textual-descriptions","title":"Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?","date":"2024-02-11","arxiv_id":"2402.07140","n_code_links":0,"syntology":null},{"paper":"/paper/chemllm-a-chemical-large-language-model","slug":"chemllm-a-chemical-large-language-model","title":"ChemLLM: A Chemical Large Language Model","date":"2024-02-10","arxiv_id":"2402.06852","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentinels-of-the-stream-unleashing-large","title":"Sentinels of the Stream: Unleashing Large Language Models for Dynamic Packet Classification in Software Defined Networks -- Position Paper","date":"2024-02-10","arxiv_id":"2402.07950","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-training-speedup-from","title":"Understanding the Training Speedup from Sampling with Approximate Losses","date":"2024-02-10","arxiv_id":"2402.07052","n_code_links":0,"syntology":null},{"paper":"/paper/culturellm-incorporating-cultural-differences","slug":"culturellm-incorporating-cultural-differences","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","date":"2024-02-09","arxiv_id":"2402.10946","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["scarelette/culturellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entgpt-linking-generative-large-language","slug":"entgpt-linking-generative-large-language","title":"EntGPT: Linking Generative Large Language Models with Knowledge Bases","date":"2024-02-09","arxiv_id":"2402.06738","n_code_links":1,"syntology":null},{"paper":"/paper/exaranker-open-synthetic-explanation-for-ir","slug":"exaranker-open-synthetic-explanation-for-ir","title":"ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs","date":"2024-02-09","arxiv_id":"2402.06334","n_code_links":1,"syntology":null},{"paper":null,"slug":"fabert-pre-training-bert-on-persian-blogs","title":"FaBERT: Pre-training BERT on Persian Blogs","date":"2024-02-09","arxiv_id":"2402.06617","n_code_links":0,"syntology":null},{"paper":"/paper/g-sciedbert-a-contextualized-llm-for-science","slug":"g-sciedbert-a-contextualized-llm-for-science","title":"G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German","date":"2024-02-09","arxiv_id":"2402.06584","n_code_links":1,"syntology":null},{"paper":null,"slug":"learn-to-be-efficient-build-structured","title":"Learn To be Efficient: Build Structured Sparsity in Large Language Models","date":"2024-02-09","arxiv_id":"2402.06126","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-assessment-of-jailbreak-attacks","slug":"comprehensive-assessment-of-jailbreak-attacks","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","date":"2024-02-08","arxiv_id":"2402.05668","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["TrustAIRLab/Comprehensive_Jailbreak_Assessment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-models-for-the-detection-of-hate","title":"Efficient Models for the Detection of Hate, Abuse and Profanity","date":"2024-02-08","arxiv_id":"2402.05624","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-stagewise-pretraining-via","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","date":"2024-02-08","arxiv_id":"2402.05913","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-principle-learning-from-mistakes","slug":"in-context-principle-learning-from-mistakes","title":"In-Context Principle Learning from Mistakes","date":"2024-02-08","arxiv_id":"2402.05403","n_code_links":1,"syntology":null},{"paper":"/paper/inksight-offline-to-online-handwriting","slug":"inksight-offline-to-online-handwriting","title":"InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write","date":"2024-02-08","arxiv_id":"2402.05804","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-recognition-for-address","title":"Named Entity Recognition for Address Extraction in Speech-to-Text Transcriptions Using Synthetic Data","date":"2024-02-08","arxiv_id":"2402.05545","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-models-for-source-code-synthesis-and","title":"Neural Models for Source Code Synthesis and Completion","date":"2024-02-08","arxiv_id":"2402.06690","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-chain-of-thought-reasoning-guided","title":"Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models","date":"2024-02-08","arxiv_id":"2402.05376","n_code_links":0,"syntology":null},{"paper":"/paper/a-hypothesis-driven-framework-for-the","slug":"a-hypothesis-driven-framework-for-the","title":"A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models","date":"2024-02-07","arxiv_id":"2402.04787","n_code_links":1,"syntology":null},{"paper":null,"slug":"aspect-based-sentiment-analysis-for-open","title":"Aspect-Based Sentiment Analysis for Open-Ended HR Survey Responses","date":"2024-02-07","arxiv_id":"2402.04812","n_code_links":0,"syntology":null},{"paper":"/paper/grandmaster-level-chess-without-search","slug":"grandmaster-level-chess-without-search","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","date":"2024-02-07","arxiv_id":"2402.04494","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-deepmind/searchless_chess"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-bert-speaks-shakespearean-english","title":"How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models","date":"2024-02-07","arxiv_id":"2402.05034","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-cross-domain-low-resource-text","title":"Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach","date":"2024-02-07","arxiv_id":"2402.04609","n_code_links":0,"syntology":null},{"paper":"/paper/long-is-more-for-alignment-a-simple-but-tough","slug":"long-is-more-for-alignment-a-simple-but-tough","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","date":"2024-02-07","arxiv_id":"2402.04833","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/long-is-more-for-alignment"],"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","unlocated"]}}},{"paper":null,"slug":"advancing-legal-reasoning-the-integration-of","title":"Advancing Legal Reasoning: The Integration of AI to Navigate Complexities and Biases in Global Jurisprudence with Semi-Automated Arbitration Processes (SAAPs)","date":"2024-02-06","arxiv_id":"2402.04140","n_code_links":0,"syntology":null},{"paper":null,"slug":"behind-the-screen-investigating-chatgpt-s","title":"Behind the Screen: Investigating ChatGPT's Dark Personality Traits and Conspiracy Beliefs","date":"2024-02-06","arxiv_id":"2402.04110","n_code_links":0,"syntology":null},{"paper":null,"slug":"cehr-gpt-generating-electronic-health-records","title":"CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines","date":"2024-02-06","arxiv_id":"2402.04400","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-mode-collapse-in-language-models","title":"Detecting Mode Collapse in Language Models via Narration","date":"2024-02-06","arxiv_id":"2402.04477","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-retrieval-processes-for-language","title":"Enhancing Retrieval Processes for Language Generation with Augmented Queries","date":"2024-02-06","arxiv_id":"2402.16874","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-an-indirect-reasoner","title":"Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning","date":"2024-02-06","arxiv_id":"2402.03667","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-moocs-graders","title":"Large Language Models As MOOCs Graders","date":"2024-02-06","arxiv_id":"2402.03776","n_code_links":0,"syntology":null},{"paper":null,"slug":"leak-cheat-repeat-data-contamination-and","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","date":"2024-02-06","arxiv_id":"2402.03927","n_code_links":0,"syntology":null},{"paper":"/paper/legallens-leveraging-llms-for-legal-violation","slug":"legallens-leveraging-llms-for-legal-violation","title":"LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text","date":"2024-02-06","arxiv_id":"2402.04335","n_code_links":1,"syntology":null},{"paper":null,"slug":"lens-a-foundation-model-for-network-traffic","title":"Lens: A Foundation Model for Network Traffic","date":"2024-02-06","arxiv_id":"2402.03646","n_code_links":0,"syntology":null},{"paper":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","n_code_links":0,"syntology":null},{"paper":"/paper/pard-permutation-invariant-autoregressive","slug":"pard-permutation-invariant-autoregressive","title":"Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation","date":"2024-02-06","arxiv_id":"2402.03687","n_code_links":1,"syntology":null},{"paper":null,"slug":"stanceosaurus-2-0-classifying-stance-towards","title":"Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation","date":"2024-02-06","arxiv_id":"2402.03642","n_code_links":0,"syntology":null},{"paper":"/paper/the-hedgehog-the-porcupine-expressive-linear","slug":"the-hedgehog-the-porcupine-expressive-linear","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","date":"2024-02-06","arxiv_id":"2402.04347","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-use-of-a-large-language-model-for","title":"The Use of a Large Language Model for Cyberbullying Detection","date":"2024-02-06","arxiv_id":"2402.04088","n_code_links":0,"syntology":null},{"paper":"/paper/training-language-models-to-generate-text","slug":"training-language-models-to-generate-text","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","date":"2024-02-06","arxiv_id":"2402.04315","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":3,"n_instrument":4,"unverified":5,"pointer_only":1,"phrase":"7 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; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["hcy123902/atg-w-fg-rw"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/accurate-and-well-calibrated-icd-code","slug":"accurate-and-well-calibrated-icd-code","title":"Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings","date":"2024-02-05","arxiv_id":"2402.03172","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gecgomes/icd_coding_msam"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/arabic-synonym-bert-based-adversarial","slug":"arabic-synonym-bert-based-adversarial","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","date":"2024-02-05","arxiv_id":"2402.03477","n_code_links":1,"syntology":null},{"paper":"/paper/c-rag-certified-generation-risks-for","slug":"c-rag-certified-generation-risks-for","title":"C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models","date":"2024-02-05","arxiv_id":"2402.03181","n_code_links":1,"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":["kangmintong/c-rag"],"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/conversation-reconstruction-attack-against","slug":"conversation-reconstruction-attack-against","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","date":"2024-02-05","arxiv_id":"2402.02987","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-textbook-question-answering-task","slug":"enhancing-textbook-question-answering-task","title":"Enhancing textual textbook question answering with large language models and retrieval augmented generation","date":"2024-02-05","arxiv_id":"2402.05128","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["hessaalawwad/plr-tqa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/financial-report-chunking-for-effective","slug":"financial-report-chunking-for-effective","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","date":"2024-02-05","arxiv_id":"2402.05131","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-pubmed-user-query-logs-for-post","title":"Harnessing PubMed User Query Logs for Post Hoc Explanations of Recommended Similar Articles","date":"2024-02-05","arxiv_id":"2402.03484","n_code_links":0,"syntology":null},{"paper":null,"slug":"lb-kbqa-large-language-model-and-bert-based","title":"LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering System","date":"2024-02-05","arxiv_id":"2402.05130","n_code_links":0,"syntology":null},{"paper":"/paper/llm-agents-in-interaction-measuring","slug":"llm-agents-in-interaction-measuring","title":"LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models","date":"2024-02-05","arxiv_id":"2402.02896","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-lingual-malaysian-embedding-leveraging","title":"Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations","date":"2024-02-05","arxiv_id":"2402.03053","n_code_links":0,"syntology":null},{"paper":"/paper/swag-storytelling-with-action-guidance","slug":"swag-storytelling-with-action-guidance","title":"SWAG: Storytelling With Action Guidance","date":"2024-02-05","arxiv_id":"2402.03483","n_code_links":1,"syntology":null},{"paper":"/paper/unimem-towards-a-unified-view-of-long-context","slug":"unimem-towards-a-unified-view-of-long-context","title":"UniMem: Towards a Unified View of Long-Context Large Language Models","date":"2024-02-05","arxiv_id":"2402.03009","n_code_links":1,"syntology":null},{"paper":"/paper/a-graph-is-worth-k-words-euclideanizing-graph","slug":"a-graph-is-worth-k-words-euclideanizing-graph","title":"A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer","date":"2024-02-04","arxiv_id":"2402.02464","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["A4Bio/GraphsGPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/autotimes-autoregressive-time-series","slug":"autotimes-autoregressive-time-series","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","date":"2024-02-04","arxiv_id":"2402.02370","n_code_links":1,"syntology":null},{"paper":null,"slug":"breaking-mlperf-training-a-case-study-on","title":"Breaking MLPerf Training: A Case Study on Optimizing BERT","date":"2024-02-04","arxiv_id":"2402.02447","n_code_links":0,"syntology":null},{"paper":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","n_code_links":1,"syntology":{"ran":13,"of":18,"n_ran_checked":13,"n_instrument":0,"unverified":5,"pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-assessment-of-tutoring-practices","title":"Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation","date":"2024-02-04","arxiv_id":"2402.14594","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-quality-matters-suicide-intention","title":"Data Quality Matters: Suicide Intention Detection on Social Media Posts Using RoBERTa-CNN","date":"2024-02-03","arxiv_id":"2402.02262","n_code_links":0,"syntology":null},{"paper":null,"slug":"de-3-bert-distance-enhanced-early-exiting-for","title":"DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks","date":"2024-02-03","arxiv_id":"2402.05948","n_code_links":0,"syntology":null},{"paper":"/paper/effibench-benchmarking-the-efficiency-of","slug":"effibench-benchmarking-the-efficiency-of","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","date":"2024-02-03","arxiv_id":"2402.02037","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["huangd1999/EffiBench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/tsis-a-supplementary-algorithm-to-t-smiles","slug":"tsis-a-supplementary-algorithm-to-t-smiles","title":"Hierarchical Structure Enhances the Convergence and Generalizability of Linear Molecular Representation","date":"2024-02-03","arxiv_id":"2402.02164","n_code_links":1,"syntology":null},{"paper":"/paper/clarifying-the-path-to-user-satisfaction-an","slug":"clarifying-the-path-to-user-satisfaction-an","title":"Clarifying the Path to User Satisfaction: An Investigation into Clarification Usefulness","date":"2024-02-02","arxiv_id":"2402.01934","n_code_links":1,"syntology":null},{"paper":null,"slug":"comet-generating-commit-messages-using-delta","title":"COMET: Generating Commit Messages using Delta Graph Context Representation","date":"2024-02-02","arxiv_id":"2402.01841","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-limitations-of-graph-reasoning","slug":"exploring-the-limitations-of-graph-reasoning","title":"Can LLMs perform structured graph reasoning?","date":"2024-02-02","arxiv_id":"2402.01805","n_code_links":1,"syntology":null},{"paper":"/paper/improving-sequential-recommendations-with","slug":"improving-sequential-recommendations-with","title":"Improving Sequential Recommendations with LLMs","date":"2024-02-02","arxiv_id":"2402.01339","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":["dh-r/llm-sequential-recommendation"],"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/llm-detector-improving-ai-generated-chinese","slug":"llm-detector-improving-ai-generated-chinese","title":"LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction Tuning","date":"2024-02-02","arxiv_id":"2402.01158","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-atp-binding-sites-in-protein","title":"Predicting ATP binding sites in protein sequences using Deep Learning and Natural Language Processing","date":"2024-02-02","arxiv_id":"2402.01829","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-end-to-end-spoken-dialog","title":"Retrieval Augmented End-to-End Spoken Dialog Models","date":"2024-02-02","arxiv_id":"2402.01828","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-unified-language-model-for","title":"CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks","date":"2024-02-02","arxiv_id":"2402.01176","n_code_links":0,"syntology":null}],"record_sha256":"ae7bf132cfd2c32883cb791186492f32b194e39d98c3ed53ea8ca86476995a85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}