{"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/35","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":35,"pages_in_order":109,"rows_per_page":100,"rows":[3401,3500],"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/34","next":"/method/attention-dropout/papers/36","papers":[{"paper":null,"slug":"hybrid-human-llm-corpus-construction-and-llm","title":"Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena","date":"2024-03-11","arxiv_id":"2403.06965","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrating-causal-graphs-with-large-language","title":"Narrating Causal Graphs with Large Language Models","date":"2024-03-11","arxiv_id":"2403.07118","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-audio-textual-diffusion-model-for","title":"An Audio-textual Diffusion Model For Converting Speech Signals Into Ultrasound Tongue Imaging Data","date":"2024-03-09","arxiv_id":"2403.05820","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-hop-knowledge-graph-reasoning","title":"Enhancing Multi-Hop Knowledge Graph Reasoning through Reward Shaping Techniques","date":"2024-03-09","arxiv_id":"2403.05801","n_code_links":0,"syntology":null},{"paper":null,"slug":"hufu-a-modality-agnositc-watermarking-system","title":"TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers","date":"2024-03-09","arxiv_id":"2403.05842","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-guided-sparse-transformer-for","title":"Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration","date":"2024-03-09","arxiv_id":"2403.05906","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-nuanced-conversation-evaluation","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","date":"2024-03-08","arxiv_id":"2403.09705","n_code_links":0,"syntology":null},{"paper":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["raybears/cot-transparency"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"piperag-fast-retrieval-augmented-generation","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","date":"2024-03-08","arxiv_id":"2403.05676","n_code_links":0,"syntology":null},{"paper":"/paper/rat-retrieval-augmented-thoughts-elicit","slug":"rat-retrieval-augmented-thoughts-elicit","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","date":"2024-03-08","arxiv_id":"2403.05313","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-quantization-on-the-robustness","title":"The Impact of Quantization on the Robustness of Transformer-based Text Classifiers","date":"2024-03-08","arxiv_id":"2403.05365","n_code_links":0,"syntology":null},{"paper":"/paper/automating-the-information-extraction-from","slug":"automating-the-information-extraction-from","title":"Automating the Information Extraction from Semi-Structured Interview Transcripts","date":"2024-03-07","arxiv_id":"2403.04819","n_code_links":1,"syntology":null},{"paper":"/paper/federated-recommendation-via-hybrid-retrieval","slug":"federated-recommendation-via-hybrid-retrieval","title":"Federated Recommendation via Hybrid Retrieval Augmented Generation","date":"2024-03-07","arxiv_id":"2403.04256","n_code_links":1,"syntology":null},{"paper":null,"slug":"feedback-generation-for-programming-exercises","title":"Feedback-Generation for Programming Exercises With GPT-4","date":"2024-03-07","arxiv_id":"2403.04449","n_code_links":0,"syntology":null},{"paper":null,"slug":"telecom-language-models-must-they-be-large","title":"Telecom Language Models: Must They Be Large?","date":"2024-03-07","arxiv_id":"2403.04666","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-hallucination-in-large-language","slug":"benchmarking-hallucination-in-large-language","title":"Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem","date":"2024-03-06","arxiv_id":"2403.03558","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-do-analytical","title":"Can Large Language Models do Analytical Reasoning?","date":"2024-03-06","arxiv_id":"2403.04031","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-asd-detection-accuracy-a-combined","slug":"enhancing-asd-detection-accuracy-a-combined","title":"Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing","date":"2024-03-06","arxiv_id":"2403.03581","n_code_links":1,"syntology":null},{"paper":"/paper/faaf-facts-as-a-function-for-the-evaluation","slug":"faaf-facts-as-a-function-for-the-evaluation","title":"FaaF: Facts as a Function for the evaluation of generated text","date":"2024-03-06","arxiv_id":"2403.03888","n_code_links":1,"syntology":null},{"paper":"/paper/galore-memory-efficient-llm-training-by","slug":"galore-memory-efficient-llm-training-by","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","date":"2024-03-06","arxiv_id":"2403.03507","n_code_links":3,"syntology":null},{"paper":null,"slug":"general2specialized-llms-translation-for-e","title":"General2Specialized LLMs Translation for E-commerce","date":"2024-03-06","arxiv_id":"2403.03689","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-enumerative-program-synthesis-with","title":"Guiding Enumerative Program Synthesis with Large Language Models","date":"2024-03-06","arxiv_id":"2403.03997","n_code_links":0,"syntology":null},{"paper":null,"slug":"japanese-english-sentence-translation","title":"Japanese-English Sentence Translation Exercises Dataset for Automatic Grading","date":"2024-03-06","arxiv_id":"2403.03396","n_code_links":0,"syntology":null},{"paper":"/paper/rapidly-developing-high-quality-instruction","slug":"rapidly-developing-high-quality-instruction","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","date":"2024-03-06","arxiv_id":"2403.03690","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-and-optimizing-educational-content","slug":"evaluating-and-optimizing-educational-content","title":"Evaluating and Optimizing Educational Content with Large Language Model Judgments","date":"2024-03-05","arxiv_id":"2403.02795","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":["StanfordAI4HI/ed-expert-simulator"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/exploring-naive-approaches-to-tell-apart-llms","slug":"exploring-naive-approaches-to-tell-apart-llms","title":"Exploring Naive Approaches to Tell Apart LLMs Productions from Human-written Text","date":"2024-03-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-event-definition-following-for-zero","title":"Improving Event Definition Following For Zero-Shot Event Detection","date":"2024-03-05","arxiv_id":"2403.02586","n_code_links":0,"syntology":null},{"paper":"/paper/jmi-at-semeval-2024-task-3-two-step-approach","slug":"jmi-at-semeval-2024-task-3-two-step-approach","title":"JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models","date":"2024-03-05","arxiv_id":"2403.04798","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":5,"n_instrument":0,"unverified":7,"pointer_only":12,"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) · 7 unverified","official":{"repos":["cmooncs/semeval-2024_multimodal_ecpe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-graphs-as-context-sources-for-llm","title":"Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations","date":"2024-03-05","arxiv_id":"2403.03008","n_code_links":0,"syntology":null},{"paper":"/paper/mathscale-scaling-instruction-tuning-for","slug":"mathscale-scaling-instruction-tuning-for","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","date":"2024-03-05","arxiv_id":"2403.02884","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-aware-semantic-cache-for-large","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","date":"2024-03-05","arxiv_id":"2403.02694","n_code_links":0,"syntology":null},{"paper":"/paper/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","n_code_links":2,"syntology":null},{"paper":null,"slug":"zero-shot-cross-lingual-document-level-event","title":"Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning","date":"2024-03-05","arxiv_id":"2403.02893","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-generation-of-multiple-choice-cloze","title":"Automated Generation of Multiple-Choice Cloze Questions for Assessing English Vocabulary Using GPT-turbo 3.5","date":"2024-03-04","arxiv_id":"2403.02078","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-architectural-design","title":"Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study","date":"2024-03-04","arxiv_id":"2403.01709","n_code_links":0,"syntology":null},{"paper":"/paper/differentially-private-synthetic-data-via-1","slug":"differentially-private-synthetic-data-via-1","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","date":"2024-03-04","arxiv_id":"2403.01749","n_code_links":2,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ai-secure/aug-pe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/eee-qa-exploring-effective-and-efficient","slug":"eee-qa-exploring-effective-and-efficient","title":"EEE-QA: Exploring Effective and Efficient Question-Answer Representations","date":"2024-03-04","arxiv_id":"2403.02176","n_code_links":1,"syntology":null},{"paper":null,"slug":"hypertext-entity-extraction-in-webpage","title":"Hypertext Entity Extraction in Webpage","date":"2024-03-04","arxiv_id":"2403.01698","n_code_links":0,"syntology":null},{"paper":null,"slug":"notellm-a-retrievable-large-language-model","title":"NoteLLM: A Retrievable Large Language Model for Note Recommendation","date":"2024-03-04","arxiv_id":"2403.01744","n_code_links":0,"syntology":null},{"paper":null,"slug":"phantom-personality-has-an-effect-on-theory","title":"PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models","date":"2024-03-04","arxiv_id":"2403.02246","n_code_links":0,"syntology":null},{"paper":"/paper/protrix-building-models-for-planning-and","slug":"protrix-building-models-for-planning-and","title":"ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context","date":"2024-03-04","arxiv_id":"2403.02177","n_code_links":1,"syntology":null},{"paper":"/paper/sciassess-benchmarking-llm-proficiency-in","slug":"sciassess-benchmarking-llm-proficiency-in","title":"SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis","date":"2024-03-04","arxiv_id":"2403.01976","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["sci-assess/sciassess"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/using-llms-for-the-extraction-and","slug":"using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","date":"2024-03-04","arxiv_id":"2403.02130","n_code_links":1,"syntology":null},{"paper":null,"slug":"vanilla-transformers-are-transfer-capability","title":"Vanilla Transformers are Transfer Capability Teachers","date":"2024-03-04","arxiv_id":"2403.01994","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-vs-retrieval-augmented-generation","slug":"fine-tuning-vs-retrieval-augmented-generation","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","date":"2024-03-03","arxiv_id":"2403.01432","n_code_links":1,"syntology":{"ran":15,"of":19,"n_ran_checked":15,"n_instrument":0,"unverified":4,"pointer_only":19,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["heydarsoudani/ragvsft"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-level-product-category-prediction","slug":"multi-level-product-category-prediction","title":"Multi-level Product Category Prediction through Text Classification","date":"2024-03-03","arxiv_id":"2403.01638","n_code_links":1,"syntology":null},{"paper":"/paper/serval-synergy-learning-between-vertical","slug":"serval-synergy-learning-between-vertical","title":"SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction","date":"2024-03-03","arxiv_id":"2403.01570","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/analysis-of-privacy-leakage-in-federated","slug":"analysis-of-privacy-leakage-in-federated","title":"Analysis of Privacy Leakage in Federated Large Language Models","date":"2024-03-02","arxiv_id":"2403.04784","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vunhatminh/fl_attacks"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/autodefense-multi-agent-llm-defense-against","slug":"autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","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":["xhmy/autodefense"],"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":"lm4opt-unveiling-the-potential-of-large","title":"LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems","date":"2024-03-02","arxiv_id":"2403.01342","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragged-edges-the-double-edged-sword-of","title":"RAGged Edges: The Double-Edged Sword of Retrieval-Augmented Chatbots","date":"2024-03-02","arxiv_id":"2403.01193","n_code_links":0,"syntology":null},{"paper":null,"slug":"atp-enabling-fast-llm-serving-via-attention","title":"ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys","date":"2024-03-01","arxiv_id":"2403.02352","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-in-large-language-models-across","title":"Gender Bias in Large Language Models across Multiple Languages","date":"2024-03-01","arxiv_id":"2403.00277","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-simultaneous-named","title":"Large Language Models for Simultaneous Named Entity Extraction and Spelling Correction","date":"2024-03-01","arxiv_id":"2403.00528","n_code_links":0,"syntology":null},{"paper":"/paper/softtiger-a-clinical-foundation-model-for","slug":"softtiger-a-clinical-foundation-model-for","title":"SoftTiger: A Clinical Foundation Model for Healthcare Workflows","date":"2024-03-01","arxiv_id":"2403.00868","n_code_links":1,"syntology":null},{"paper":"/paper/artist-automated-text-simplification-for-task","slug":"artist-automated-text-simplification-for-task","title":"ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality","date":"2024-02-29","arxiv_id":"2402.18797","n_code_links":1,"syntology":null},{"paper":null,"slug":"crafting-knowledge-exploring-the-creative","title":"Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Engines","date":"2024-02-29","arxiv_id":"2402.19421","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-pre-trained-language-models-for-3","slug":"leveraging-pre-trained-language-models-for-3","title":"Leveraging pre-trained language models for code generation","date":"2024-02-29","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-ensemble-optimal-large-language-model","title":"LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction","date":"2024-02-29","arxiv_id":"2403.00863","n_code_links":0,"syntology":null},{"paper":null,"slug":"paecter-patent-level-representation-learning","title":"PaECTER: Patent-level Representation Learning using Citation-informed Transformers","date":"2024-02-29","arxiv_id":"2402.19411","n_code_links":0,"syntology":null},{"paper":null,"slug":"pelle-encoder-based-language-models-for","title":"PeLLE: Encoder-based language models for Brazilian Portuguese based on open data","date":"2024-02-29","arxiv_id":"2402.19204","n_code_links":0,"syntology":null},{"paper":null,"slug":"proc2pddl-open-domain-planning","title":"PROC2PDDL: Open-Domain Planning Representations from Texts","date":"2024-02-29","arxiv_id":"2403.00092","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-chatgpt-for-translation-a","title":"Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts","date":"2024-02-29","arxiv_id":"2403.00127","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-for-ai","slug":"retrieval-augmented-generation-for-ai","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","date":"2024-02-29","arxiv_id":"2402.19473","n_code_links":3,"syntology":null},{"paper":null,"slug":"rl-gpt-integrating-reinforcement-learning-and","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","date":"2024-02-29","arxiv_id":"2402.19299","n_code_links":0,"syntology":null},{"paper":null,"slug":"vixen-visual-text-comparison-network-for","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","date":"2024-02-29","arxiv_id":"2402.19119","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-improve-the-state-of-prior","title":"Can GPT Improve the State of Prior Authorization via Guideline Based Automated Question Answering?","date":"2024-02-28","arxiv_id":"2402.18419","n_code_links":0,"syntology":null},{"paper":"/paper/clustering-and-ranking-diversity-preserved","slug":"clustering-and-ranking-diversity-preserved","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","date":"2024-02-28","arxiv_id":"2402.18191","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"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) · 3 unverified","official":{"repos":["ironbeliever/car"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decomposed-prompting-unveiling-multilingual","title":"Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models","date":"2024-02-28","arxiv_id":"2402.18397","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-fairness-unveiling-llm-s-potential","title":"Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification","date":"2024-02-28","arxiv_id":"2402.18502","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-free-adaptive-global-pruning-for-pre","slug":"gradient-free-adaptive-global-pruning-for-pre","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","date":"2024-02-28","arxiv_id":"2402.17946","n_code_links":2,"syntology":{"ran":3,"of":9,"n_ran_checked":2,"n_instrument":1,"unverified":6,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["baithebest/adagp","baithebest/sparsellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/keeping-llms-aligned-after-fine-tuning-the","slug":"keeping-llms-aligned-after-fine-tuning-the","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","date":"2024-02-28","arxiv_id":"2402.18540","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vfleaking/ptst"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"orchid-flexible-and-data-dependent","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","date":"2024-02-28","arxiv_id":"2402.18508","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-based-full-length-wikipedia","slug":"retrieval-based-full-length-wikipedia","title":"WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario","date":"2024-02-28","arxiv_id":"2402.18264","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-information-refinement-training","slug":"unsupervised-information-refinement-training","title":"Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation","date":"2024-02-28","arxiv_id":"2402.18150","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"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) · 2 unverified","official":{"repos":["xsc1234/info-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-language-model-based-framework-for-new","slug":"a-language-model-based-framework-for-new","title":"A Language Model based Framework for New Concept Placement in Ontologies","date":"2024-02-27","arxiv_id":"2402.17897","n_code_links":1,"syntology":null},{"paper":null,"slug":"cocoa-cbt-based-conversational-counseling","title":"COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt","date":"2024-02-27","arxiv_id":"2402.17546","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-detection-method-for-large","title":"Deep Learning Detection Method for Large Language Models-Generated Scientific Content","date":"2024-02-27","arxiv_id":"2403.00828","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotional-voice-messages-emovome-database","title":"Emotional Voice Messages (EMOVOME) database: emotion recognition in spontaneous voice messages","date":"2024-02-27","arxiv_id":"2402.17496","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-very-long-term-conversational","slug":"evaluating-very-long-term-conversational","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","date":"2024-02-27","arxiv_id":"2402.17753","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/follow-my-instruction-and-spill-the-beans","slug":"follow-my-instruction-and-spill-the-beans","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","date":"2024-02-27","arxiv_id":"2402.17840","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhentingqi/rag-privacy"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/jmlr-joint-medical-llm-and-retrieval-training","slug":"jmlr-joint-medical-llm-and-retrieval-training","title":"JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability","date":"2024-02-27","arxiv_id":"2402.17887","n_code_links":1,"syntology":null},{"paper":"/paper/linguistic-knowledge-can-enhance-encoder","slug":"linguistic-knowledge-can-enhance-encoder","title":"Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)","date":"2024-02-27","arxiv_id":"2402.17608","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-vision-language-stem-skills-of","slug":"measuring-vision-language-stem-skills-of","title":"Measuring Vision-Language STEM Skills of Neural Models","date":"2024-02-27","arxiv_id":"2402.17205","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stemdataset/STEM"],"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/multi-task-media-bias-analysis-generalization","slug":"multi-task-media-bias-analysis-generalization","title":"MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressions","date":"2024-02-27","arxiv_id":"2403.07910","n_code_links":1,"syntology":null},{"paper":"/paper/rear-a-relevance-aware-retrieval-augmented","slug":"rear-a-relevance-aware-retrieval-augmented","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","date":"2024-02-27","arxiv_id":"2402.17497","n_code_links":1,"syntology":{"ran":5,"of":14,"n_ran_checked":5,"n_instrument":0,"unverified":9,"pointer_only":14,"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) · 9 unverified","official":{"repos":["rucaibox/rear"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"skt5scisumm-a-hybrid-generative-approach-for","title":"SKT5SciSumm -- Revisiting Extractive-Generative Approach for Multi-Document Scientific Summarization","date":"2024-02-27","arxiv_id":"2402.17311","n_code_links":0,"syntology":null},{"paper":"/paper/variational-learning-is-effective-for-large","slug":"variational-learning-is-effective-for-large","title":"Variational Learning is Effective for Large Deep Networks","date":"2024-02-27","arxiv_id":"2402.17641","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 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["team-approx-bayes/ivon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adaptation-of-biomedical-and-clinical","slug":"adaptation-of-biomedical-and-clinical","title":"Adaptation of Biomedical and Clinical Pretrained Models to French Long Documents: A Comparative Study","date":"2024-02-26","arxiv_id":"2402.16689","n_code_links":1,"syntology":null},{"paper":"/paper/an-integrated-data-processing-framework-for","slug":"an-integrated-data-processing-framework-for","title":"An Integrated Data Processing Framework for Pretraining Foundation Models","date":"2024-02-26","arxiv_id":"2402.16358","n_code_links":2,"syntology":null},{"paper":"/paper/asymmetry-in-low-rank-adapters-of-foundation","slug":"asymmetry-in-low-rank-adapters-of-foundation","title":"Asymmetry in Low-Rank Adapters of Foundation Models","date":"2024-02-26","arxiv_id":"2402.16842","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":["Jiacheng-Zhu-AIML/AsymmetryLoRA"],"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":null,"slug":"esg-sentiment-analysis-comparing-human-and","title":"ESG Sentiment Analysis: comparing human and language model performance including GPT","date":"2024-02-26","arxiv_id":"2402.16650","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-rags-to-riches-using-large-language","title":"From RAGs to riches: Using large language models to write documents for clinical trials","date":"2024-02-26","arxiv_id":"2402.16406","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-systems","slug":"retrieval-augmented-generation-systems","title":"Retrieval Augmented Generation Systems: Automatic Dataset Creation, Evaluation and Boolean Agent Setup","date":"2024-02-26","arxiv_id":"2403.00820","n_code_links":1,"syntology":null},{"paper":"/paper/chatmusician-understanding-and-generating","slug":"chatmusician-understanding-and-generating","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","date":"2024-02-25","arxiv_id":"2402.16153","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hf-lin/ChatMusician"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-learning-approaches-for-improving","title":"Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research","date":"2024-02-25","arxiv_id":"2402.16038","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-classification-in-short-english-texts","title":"Emotion Classification in Short English Texts using Deep Learning Techniques","date":"2024-02-25","arxiv_id":"2402.16034","n_code_links":0,"syntology":null},{"paper":"/paper/fusechat-knowledge-fusion-of-chat-models","slug":"fusechat-knowledge-fusion-of-chat-models","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","date":"2024-02-25","arxiv_id":"2402.16107","n_code_links":2,"syntology":null},{"paper":null,"slug":"hitting-probe-rty-with-non-linearity-and-more","title":"Hitting \"Probe\"rty with Non-Linearity, and More","date":"2024-02-25","arxiv_id":"2402.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-can-defend-themselves-against","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper","date":"2024-02-24","arxiv_id":"2402.15727","n_code_links":0,"syntology":null}],"record_sha256":"4badefb38fa20f471b3936bff4d73926e220433e3606292babc6edd2ae44b1a2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}