{"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/27","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":27,"pages_in_order":109,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/method/attention-dropout/papers/28","papers":[{"paper":"/paper/unlocking-continual-learning-abilities-in","slug":"unlocking-continual-learning-abilities-in","title":"Unlocking Continual Learning Abilities in Language Models","date":"2024-06-25","arxiv_id":"2406.17245","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":["wenyudu/migu"],"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":"what-do-the-circuits-mean-a-knowledge-edit","title":"Understanding Language Model Circuits through Knowledge Editing","date":"2024-06-25","arxiv_id":"2406.17241","n_code_links":0,"syntology":null},{"paper":"/paper/attention-instruction-amplifying-attention-in","slug":"attention-instruction-amplifying-attention-in","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","date":"2024-06-24","arxiv_id":"2406.17095","n_code_links":1,"syntology":null},{"paper":"/paper/dreambench-a-human-aligned-benchmark-for","slug":"dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","date":"2024-06-24","arxiv_id":"2406.16855","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuangpeng/dreambench_plus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluation-of-instruction-following-ability","title":"Evaluation of Instruction-Following Ability for Large Language Models on Story-Ending Generation","date":"2024-06-24","arxiv_id":"2406.16356","n_code_links":0,"syntology":null},{"paper":"/paper/finding-transformer-circuits-with-edge","slug":"finding-transformer-circuits-with-edge","title":"Finding Transformer Circuits with Edge Pruning","date":"2024-06-24","arxiv_id":"2406.16778","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":3,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/edge-pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"modeling-a-novel-dataset-for-testing","title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models","date":"2024-06-24","arxiv_id":"2406.17038","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-role-of-long-tail-knowledge-in","title":"On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models","date":"2024-06-24","arxiv_id":"2406.16367","n_code_links":0,"syntology":null},{"paper":"/paper/panza-a-personalized-text-writing-assistant","slug":"panza-a-personalized-text-writing-assistant","title":"Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant","date":"2024-06-24","arxiv_id":"2407.10994","n_code_links":1,"syntology":null},{"paper":null,"slug":"plagbench-exploring-the-duality-of-large","title":"PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection","date":"2024-06-24","arxiv_id":"2406.16288","n_code_links":0,"syntology":null},{"paper":"/paper/ragnarok-a-reusable-rag-framework-and","slug":"ragnarok-a-reusable-rag-framework-and","title":"Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track","date":"2024-06-24","arxiv_id":"2406.16828","n_code_links":2,"syntology":{"ran":19,"of":23,"n_ran_checked":19,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["castorini/ragnarok"],"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":["listed","official"]}}},{"paper":"/paper/the-gpt-writingprompts-dataset-a-comparative","slug":"the-gpt-writingprompts-dataset-a-comparative","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","date":"2024-06-24","arxiv_id":"2406.16767","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-graph-based-cross-document","slug":"towards-better-graph-based-cross-document","title":"Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing","date":"2024-06-24","arxiv_id":"2406.16529","n_code_links":1,"syntology":null},{"paper":"/paper/unambiguous-recognition-should-not-rely","slug":"unambiguous-recognition-should-not-rely","title":"MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data","date":"2024-06-24","arxiv_id":"2406.17148","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-ensemble-methods-for-news","title":"Evaluating Ensemble Methods for News Recommender Systems","date":"2024-06-23","arxiv_id":"2406.16106","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-the","title":"Evaluating the Effectiveness of the Foundational Models for Q&A Classification in Mental Health care","date":"2024-06-23","arxiv_id":"2406.15966","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval2000-benchmarking-and-improving","title":"GraphEval2000: Benchmarking and Improving Large Language Models on Graph Datasets","date":"2024-06-23","arxiv_id":"2406.16176","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-speaker-multi-lingual-voice-cloning","title":"A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge","date":"2024-06-22","arxiv_id":"2406.17801","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-visualizations-with","title":"Can LLMs Generate Visualizations with Dataless Prompts?","date":"2024-06-22","arxiv_id":"2406.17805","n_code_links":0,"syntology":null},{"paper":"/paper/ss-bench-a-benchmark-for-social-story","slug":"ss-bench-a-benchmark-for-social-story","title":"SS-GEN: A Social Story Generation Framework with Large Language Models","date":"2024-06-22","arxiv_id":"2406.15695","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-gpt-based-code-review-system-for","title":"A GPT-based Code Review System for Programming Language Learning","date":"2024-06-21","arxiv_id":"2407.04722","n_code_links":0,"syntology":null},{"paper":"/paper/a-tale-of-trust-and-accuracy-base-vs-instruct","slug":"a-tale-of-trust-and-accuracy-base-vs-instruct","title":"A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems","date":"2024-06-21","arxiv_id":"2406.14972","n_code_links":1,"syntology":null},{"paper":null,"slug":"anime-popularity-prediction-before-huge","title":"Anime Popularity Prediction Before Huge Investments: a Multimodal Approach Using Deep Learning","date":"2024-06-21","arxiv_id":"2406.16961","n_code_links":0,"syntology":null},{"paper":null,"slug":"giusberto-a-legal-language-model-for-personal","title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions","date":"2024-06-21","arxiv_id":"2406.15032","n_code_links":0,"syntology":null},{"paper":null,"slug":"longrag-enhancing-retrieval-augmented","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","date":"2024-06-21","arxiv_id":"2406.15319","n_code_links":0,"syntology":null},{"paper":null,"slug":"pistis-rag-a-scalable-cascading-framework","title":"Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback","date":"2024-06-21","arxiv_id":"2407.00072","n_code_links":0,"syntology":null},{"paper":"/paper/augmenting-query-and-passage-for-retrieval","slug":"augmenting-query-and-passage-for-retrieval","title":"QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs","date":"2024-06-20","arxiv_id":"2406.14277","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["kmswin1/qpaug"],"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":"chatgpt-as-research-scientist-probing-gpt-s","title":"ChatGPT as Research Scientist: Probing GPT's Capabilities as a Research Librarian, Research Ethicist, Data Generator and Data Predictor","date":"2024-06-20","arxiv_id":"2406.14765","n_code_links":0,"syntology":null},{"paper":"/paper/coderag-bench-can-retrieval-augment-code","slug":"coderag-bench-can-retrieval-augment-code","title":"CodeRAG-Bench: Can Retrieval Augment Code Generation?","date":"2024-06-20","arxiv_id":"2406.14497","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["code-rag-bench/code-rag-bench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cryptogpt-a-7b-model-rivaling-gpt-4-in-the","title":"CryptoGPT: a 7B model rivaling GPT-4 in the task of analyzing and classifying real-time financial news","date":"2024-06-20","arxiv_id":"2406.14039","n_code_links":0,"syntology":null},{"paper":"/paper/diras-efficient-llm-assisted-annotation-of","slug":"diras-efficient-llm-assisted-annotation-of","title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","date":"2024-06-20","arxiv_id":"2406.14162","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-implicit-bias-in-large-language","slug":"evaluating-implicit-bias-in-large-language","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","date":"2024-06-20","arxiv_id":"2406.14023","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-rag-fusion-with-ragelo-an","slug":"evaluating-rag-fusion-with-ragelo-an","title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","date":"2024-06-20","arxiv_id":"2406.14783","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zetaalphavector/ragelo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-ai-for-enhancing-active-learning","title":"Generative AI for Enhancing Active Learning in Education: A Comparative Study of GPT-3.5 and GPT-4 in Crafting Customized Test Questions","date":"2024-06-20","arxiv_id":"2406.13903","n_code_links":0,"syntology":null},{"paper":null,"slug":"healing-powers-of-bert-how-task-specific-fine","title":"Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models","date":"2024-06-20","arxiv_id":"2406.14459","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-compute-the-probability-of-a-word","slug":"how-to-compute-the-probability-of-a-word","title":"How to Compute the Probability of a Word","date":"2024-06-20","arxiv_id":"2406.14561","n_code_links":2,"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":["tpimentelms/probability-of-a-word"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"identifying-user-goals-from-ui-trajectories","title":"Identifying User Goals from UI Trajectories","date":"2024-06-20","arxiv_id":"2406.14314","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-plan-for-retrieval-augmented","slug":"learning-to-plan-for-retrieval-augmented","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","date":"2024-06-20","arxiv_id":"2406.14282","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjukg/lpkg"],"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/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":3,"n_instrument":3,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/persuasiveness-of-generated-free-text","slug":"persuasiveness-of-generated-free-text","title":"Persuasiveness of Generated Free-Text Rationales in Subjective Decisions: A Case Study on Pairwise Argument Ranking","date":"2024-06-20","arxiv_id":"2406.13905","n_code_links":1,"syntology":null},{"paper":"/paper/prism-a-framework-for-decoupling-and","slug":"prism-a-framework-for-decoupling-and","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","date":"2024-06-20","arxiv_id":"2406.14544","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["sparksjoe/prism"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"relation-extraction-with-fine-tuned-large","title":"Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks","date":"2024-06-20","arxiv_id":"2406.14745","n_code_links":0,"syntology":null},{"paper":null,"slug":"scidmt-a-large-scale-corpus-for-detecting","title":"SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions","date":"2024-06-20","arxiv_id":"2406.14756","n_code_links":0,"syntology":null},{"paper":"/paper/can-long-context-language-models-subsume","slug":"can-long-context-language-models-subsume","title":"Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?","date":"2024-06-19","arxiv_id":"2406.13121","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-deepmind/loft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fine-tuning-berts-for-definition-extraction","title":"Fine-Tuning BERTs for Definition Extraction from Mathematical Text","date":"2024-06-19","arxiv_id":"2406.13827","n_code_links":0,"syntology":null},{"paper":null,"slug":"forag-factuality-optimized-retrieval","title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","date":"2024-06-19","arxiv_id":"2406.13779","n_code_links":0,"syntology":null},{"paper":"/paper/instructrag-instructing-retrieval-augmented","slug":"instructrag-instructing-retrieval-augmented","title":"InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales","date":"2024-06-19","arxiv_id":"2406.13629","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["weizhepei/instructrag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/model-internals-based-answer-attribution-for","slug":"model-internals-based-answer-attribution-for","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","date":"2024-06-19","arxiv_id":"2406.13663","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["betswish/mirage"],"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-meta-rag-improving-rag-for-multi-hop","slug":"multi-meta-rag-improving-rag-for-multi-hop","title":"Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata","date":"2024-06-19","arxiv_id":"2406.13213","n_code_links":1,"syntology":null},{"paper":"/paper/on-ai-inspired-ui-design","slug":"on-ai-inspired-ui-design","title":"On AI-Inspired UI-Design","date":"2024-06-19","arxiv_id":"2406.13631","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-generative-large-language-models-for","title":"Open Generative Large Language Models for Galician","date":"2024-06-19","arxiv_id":"2406.13893","n_code_links":0,"syntology":null},{"paper":"/paper/part-aware-unified-representation-of-language-1","slug":"part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","arxiv_id":"2406.13327","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["azzh1/purls"],"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/r-2ag-incorporating-retrieval-information","slug":"r-2ag-incorporating-retrieval-information","title":"R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation","date":"2024-06-19","arxiv_id":"2406.13249","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"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) · 2 unverified","official":{"repos":["yefd/RRAG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wikicontradict-a-benchmark-for-evaluating","title":"WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia","date":"2024-06-19","arxiv_id":"2406.13805","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-rags-to-rich-parameters-probing-how","title":"From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries","date":"2024-06-18","arxiv_id":"2406.12824","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-educational-materials-with","title":"Generating Educational Materials with Different Levels of Readability using LLMs","date":"2024-06-18","arxiv_id":"2406.12787","n_code_links":0,"syntology":null},{"paper":null,"slug":"intermediate-distillation-data-efficient","title":"Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval","date":"2024-06-18","arxiv_id":"2406.12169","n_code_links":0,"syntology":null},{"paper":"/paper/ipeval-a-bilingual-intellectual-property","slug":"ipeval-a-bilingual-intellectual-property","title":"IPEval: A Bilingual Intellectual Property Agency Consultation Evaluation Benchmark for Large Language Models","date":"2024-06-18","arxiv_id":"2406.12386","n_code_links":1,"syntology":null},{"paper":"/paper/planrag-a-plan-then-retrieval-augmented","slug":"planrag-a-plan-then-retrieval-augmented","title":"PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers","date":"2024-06-18","arxiv_id":"2406.12430","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["myeon9h/planrag"],"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":"retrieval-augmented-generation-for-generative","title":"Retrieval-Augmented Generation for Generative Artificial Intelligence in Medicine","date":"2024-06-18","arxiv_id":"2406.12449","n_code_links":0,"syntology":null},{"paper":null,"slug":"richrag-crafting-rich-responses-for-multi","title":"RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation","date":"2024-06-18","arxiv_id":"2406.12566","n_code_links":0,"syntology":null},{"paper":"/paper/towards-a-client-centered-assessment-of-llm","slug":"towards-a-client-centered-assessment-of-llm","title":"Towards a Client-Centered Assessment of LLM Therapists by Client Simulation","date":"2024-06-18","arxiv_id":"2406.12266","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wangjs9/clientcast"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unified-active-retrieval-for-retrieval","slug":"unified-active-retrieval-for-retrieval","title":"Unified Active Retrieval for Retrieval Augmented Generation","date":"2024-06-18","arxiv_id":"2406.12534","n_code_links":1,"syntology":null},{"paper":null,"slug":"urbanllm-autonomous-urban-activity-planning","title":"UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models","date":"2024-06-18","arxiv_id":"2406.12360","n_code_links":0,"syntology":null},{"paper":null,"slug":"vernacular-i-barely-know-her-challenges-with","title":"Vernacular? I Barely Know Her: Challenges with Style Control and Stereotyping","date":"2024-06-18","arxiv_id":"2406.12679","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-makes-two-models-think-alike","title":"What Makes Two Language Models Think Alike?","date":"2024-06-18","arxiv_id":"2406.12620","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-gotta-be-a-doctor-lin-an-investigation-of","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","date":"2024-06-18","arxiv_id":"2406.12232","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-boundaries-investigating-the-effects","title":"Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance","date":"2024-06-17","arxiv_id":"2406.11139","n_code_links":0,"syntology":null},{"paper":"/paper/building-another-spanish-dictionary-this-time","slug":"building-another-spanish-dictionary-this-time","title":"Building another Spanish dictionary, this time with GPT-4","date":"2024-06-17","arxiv_id":"2406.11218","n_code_links":1,"syntology":null},{"paper":"/paper/cram-credibility-aware-attention-modification","slug":"cram-credibility-aware-attention-modification","title":"CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG","date":"2024-06-17","arxiv_id":"2406.11497","n_code_links":1,"syntology":null},{"paper":null,"slug":"cultural-conditioning-or-placebo-on-the","title":"Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting","date":"2024-06-17","arxiv_id":"2406.11661","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-biomedical-knowledge-retrieval","title":"SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation","date":"2024-06-17","arxiv_id":"2406.11258","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-text-classification-through-llm","slug":"enhancing-text-classification-through-llm","title":"Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation","date":"2024-06-17","arxiv_id":"2406.12114","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-the-increase-in-emissions-caused","title":"Estimating the Increase in Emissions caused by AI-augmented Search","date":"2024-06-17","arxiv_id":"2407.16894","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-open-language-models-across-task","slug":"evaluating-open-language-models-across-task","title":"Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?","date":"2024-06-17","arxiv_id":"2406.11402","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-efficacy-of-open-source-llms","slug":"evaluating-the-efficacy-of-open-source-llms","title":"Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability","date":"2024-06-17","arxiv_id":"2406.11424","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-safety-utility-trade-offs-in","title":"Exploring Safety-Utility Trade-Offs in Personalized Language Models","date":"2024-06-17","arxiv_id":"2406.11107","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-or-fine-failing-debunking","title":"Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models","date":"2024-06-17","arxiv_id":"2406.11201","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-powered-elicitation-interview-script","title":"GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training","date":"2024-06-17","arxiv_id":"2406.11439","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-multi-agent-debate-with-sparse","title":"Improving Multi-Agent Debate with Sparse Communication Topology","date":"2024-06-17","arxiv_id":"2406.11776","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-annotator-bias-in-large","slug":"investigating-annotator-bias-in-large","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","date":"2024-06-17","arxiv_id":"2406.11109","n_code_links":3,"syntology":null},{"paper":null,"slug":"iterative-utility-judgment-framework-via-llms","title":"Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy","date":"2024-06-17","arxiv_id":"2406.11290","n_code_links":0,"syntology":null},{"paper":null,"slug":"jobfair-a-framework-for-benchmarking-gender","title":"JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models","date":"2024-06-17","arxiv_id":"2406.15484","n_code_links":0,"syntology":null},{"paper":null,"slug":"promises-outlooks-and-challenges-of-diffusion","title":"Promises, Outlooks and Challenges of Diffusion Language Modeling","date":"2024-06-17","arxiv_id":"2406.11473","n_code_links":0,"syntology":null},{"paper":"/paper/r-eval-a-unified-toolkit-for-evaluating","slug":"r-eval-a-unified-toolkit-for-evaluating","title":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models","date":"2024-06-17","arxiv_id":"2406.11681","n_code_links":1,"syntology":null},{"paper":"/paper/satyrn-a-platform-for-analytics-augmented","slug":"satyrn-a-platform-for-analytics-augmented","title":"Satyrn: A Platform for Analytics Augmented Generation","date":"2024-06-17","arxiv_id":"2406.12069","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-the-codebook-size-of-vqgan-to-100000","slug":"scaling-the-codebook-size-of-vqgan-to-100000","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","date":"2024-06-17","arxiv_id":"2406.11837","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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zh460045050/vqgan-lc"],"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","unlocated"]}}},{"paper":null,"slug":"self-and-cross-model-distillation-for-llms","title":"Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment","date":"2024-06-17","arxiv_id":"2406.11285","n_code_links":0,"syntology":null},{"paper":"/paper/textit-refiner-restructure-retrieval-content","slug":"textit-refiner-restructure-retrieval-content","title":"Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities","date":"2024-06-17","arxiv_id":"2406.11357","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allen-li1231/refiner-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/trace-the-evidence-constructing-knowledge","slug":"trace-the-evidence-constructing-knowledge","title":"TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation","date":"2024-06-17","arxiv_id":"2406.11460","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jyfang6/trace"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/welldunn-on-the-robustness-and-explainability","slug":"welldunn-on-the-robustness-and-explainability","title":"WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions","date":"2024-06-17","arxiv_id":"2406.12058","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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vedantpalit/WellDunn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-supermarket-robot-interaction-a","title":"Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents","date":"2024-06-16","arxiv_id":"2406.11047","n_code_links":0,"syntology":null},{"paper":null,"slug":"exposing-the-achilles-heel-evaluating-llms","title":"Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning","date":"2024-06-16","arxiv_id":"2406.10834","n_code_links":0,"syntology":null},{"paper":"/paper/generating-tables-from-the-parametric","slug":"generating-tables-from-the-parametric","title":"Generating Tables from the Parametric Knowledge of Language Models","date":"2024-06-16","arxiv_id":"2406.10922","n_code_links":1,"syntology":null},{"paper":null,"slug":"grading-massive-open-online-courses-using","title":"Grading Massive Open Online Courses Using Large Language Models","date":"2024-06-16","arxiv_id":"2406.11102","n_code_links":0,"syntology":null},{"paper":"/paper/kgpa-robustness-evaluation-for-large-language","slug":"kgpa-robustness-evaluation-for-large-language","title":"KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs","date":"2024-06-16","arxiv_id":"2406.10802","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-automatic-milestone","title":"Large Language Models for Automatic Milestone Detection in Group Discussions","date":"2024-06-16","arxiv_id":"2406.10842","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-the-understandability-of","slug":"predicting-the-understandability-of","title":"Predicting the Understandability of Computational Notebooks through Code Metrics Analysis","date":"2024-06-16","arxiv_id":"2406.10989","n_code_links":1,"syntology":null},{"paper":null,"slug":"ptt5-v2-a-closer-look-at-continued","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","date":"2024-06-16","arxiv_id":"2406.10806","n_code_links":0,"syntology":null},{"paper":"/paper/sharelora-parameter-efficient-and-robust","slug":"sharelora-parameter-efficient-and-robust","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.10785","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Rain9876/ShareLoRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"ae6d36c1bf1fefea3866157aae72e5795722aceca7b8d35e0eca7990b20a98e0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}