{"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/18","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":18,"pages_in_order":109,"rows_per_page":100,"rows":[1701,1800],"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/17","next":"/method/attention-dropout/papers/19","papers":[{"paper":"/paper/seislm-a-foundation-model-for-seismic","slug":"seislm-a-foundation-model-for-seismic","title":"SeisLM: a Foundation Model for Seismic Waveforms","date":"2024-10-21","arxiv_id":"2410.15765","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-models-for-qualitative-and","title":"Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process","date":"2024-10-21","arxiv_id":"2410.15884","n_code_links":0,"syntology":null},{"paper":"/paper/who-s-who-large-language-models-meet","slug":"who-s-who-large-language-models-meet","title":"Who's Who: Large Language Models Meet Knowledge Conflicts in Practice","date":"2024-10-21","arxiv_id":"2410.15737","n_code_links":1,"syntology":null},{"paper":"/paper/brief-bridging-retrieval-and-inference-for","slug":"brief-bridging-retrieval-and-inference-for","title":"BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression","date":"2024-10-20","arxiv_id":"2410.15277","n_code_links":1,"syntology":null},{"paper":"/paper/contextual-augmented-multi-model-programming","slug":"contextual-augmented-multi-model-programming","title":"Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot Framework","date":"2024-10-20","arxiv_id":"2410.15285","n_code_links":1,"syntology":null},{"paper":null,"slug":"contregen-context-driven-tree-structured","title":"ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation","date":"2024-10-20","arxiv_id":"2410.15511","n_code_links":0,"syntology":null},{"paper":"/paper/do-rag-systems-cover-what-matters-evaluating","slug":"do-rag-systems-cover-what-matters-evaluating","title":"Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage","date":"2024-10-20","arxiv_id":"2410.15531","n_code_links":1,"syntology":null},{"paper":"/paper/does-chatgpt-have-a-poetic-style","slug":"does-chatgpt-have-a-poetic-style","title":"Does ChatGPT Have a Poetic Style?","date":"2024-10-20","arxiv_id":"2410.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-consistencies-in-llm-responses","title":"Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering","date":"2024-10-20","arxiv_id":"2410.15440","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmcs-a-multimodal-medical-diagnosis-system","title":"MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation","date":"2024-10-20","arxiv_id":"2410.15403","n_code_links":0,"syntology":null},{"paper":null,"slug":"sdp4bit-toward-4-bit-communication","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","date":"2024-10-20","arxiv_id":"2410.15526","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveiling-and-consulting-core-experts-in","title":"Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs","date":"2024-10-20","arxiv_id":"2410.15438","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-machine-unlearning-meets-retrieval","title":"When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?","date":"2024-10-20","arxiv_id":"2410.15267","n_code_links":0,"syntology":null},{"paper":null,"slug":"bias-amplification-language-models-as","title":"Bias Amplification: Language Models as Increasingly Biased Media","date":"2024-10-19","arxiv_id":"2410.15234","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-p300-speller-performance-using","slug":"evaluation-of-p300-speller-performance-using","title":"Evaluation Of P300 Speller Performance Using Large Language Models Along With Cross-Subject Training","date":"2024-10-19","arxiv_id":"2410.15161","n_code_links":1,"syntology":null},{"paper":"/paper/mccoder-streamlining-motion-control-with-llm","slug":"mccoder-streamlining-motion-control-with-llm","title":"MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification","date":"2024-10-19","arxiv_id":"2410.15154","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-gat-cancer-document-classification","title":"Medical-GAT: Cancer Document Classification Leveraging Graph-Based Residual Network for Scenarios with Limited Data","date":"2024-10-19","arxiv_id":"2410.15198","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-genre-aware-article-scoring-and","title":"Automated Genre-Aware Article Scoring and Feedback Using Large Language Models","date":"2024-10-18","arxiv_id":"2410.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"backdoored-retrievers-for-prompt-injection","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","date":"2024-10-18","arxiv_id":"2410.14479","n_code_links":0,"syntology":null},{"paper":null,"slug":"effects-of-soft-domain-transfer-and-named","title":"Effects of Soft-Domain Transfer and Named Entity Information on Deception Detection","date":"2024-10-18","arxiv_id":"2410.14814","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-contrastive-learning-via-cluster","title":"Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification","date":"2024-10-18","arxiv_id":"2410.18130","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-regularization-of-sharpness-aware","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","date":"2024-10-18","arxiv_id":"2410.14802","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-retrieval-augmented-generation","title":"Optimizing Retrieval-Augmented Generation with Elasticsearch for Enhanced Question-Answering Systems","date":"2024-10-18","arxiv_id":"2410.14167","n_code_links":0,"syntology":null},{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"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":null}},{"paper":"/paper/rag-confusionqa-a-benchmark-for-evaluating","slug":"rag-confusionqa-a-benchmark-for-evaluating","title":"ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions","date":"2024-10-18","arxiv_id":"2410.14567","n_code_links":1,"syntology":null},{"paper":"/paper/real-time-fake-news-from-adversarial-feedback","slug":"real-time-fake-news-from-adversarial-feedback","title":"Real-time Fake News from Adversarial Feedback","date":"2024-10-18","arxiv_id":"2410.14651","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-based-on-roberta-for","title":"Sentiment Analysis Based on RoBERTa for Amazon Review: An Empirical Study on Decision Making","date":"2024-10-18","arxiv_id":"2411.00796","n_code_links":0,"syntology":null},{"paper":"/paper/st-moe-bert-a-spatial-temporal-mixture-of","slug":"st-moe-bert-a-spatial-temporal-mixture-of","title":"ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction","date":"2024-10-18","arxiv_id":"2410.14099","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["he-h/HuMob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-systematic-investigation-of-knowledge","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","date":"2024-10-17","arxiv_id":"2410.13258","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-ai-generated-texts-in-cross-domains","slug":"detecting-ai-generated-texts-in-cross-domains","title":"Detecting AI-Generated Texts in Cross-Domains","date":"2024-10-17","arxiv_id":"2410.13966","n_code_links":1,"syntology":null},{"paper":"/paper/enhanced-prompt-leveraged-weakly-supervised","slug":"enhanced-prompt-leveraged-weakly-supervised","title":"EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything","date":"2024-10-17","arxiv_id":"2410.13621","n_code_links":2,"syntology":null},{"paper":null,"slug":"enhancing-text-generation-in-joint-nlg-nlu","title":"Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques","date":"2024-10-17","arxiv_id":"2410.13498","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-self-generated-documents-for","title":"Evaluating Self-Generated Documents for Enhancing Retrieval-Augmented Generation with Large Language Models","date":"2024-10-17","arxiv_id":"2410.13192","n_code_links":0,"syntology":null},{"paper":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","n_code_links":2,"syntology":null},{"paper":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-temporal-representations-for","title":"Integrating Temporal Representations for Dynamic Memory Retrieval and Management in Large Language Models","date":"2024-10-17","arxiv_id":"2410.13553","n_code_links":0,"syntology":null},{"paper":null,"slug":"jailbreaking-llm-controlled-robots","title":"Jailbreaking LLM-Controlled Robots","date":"2024-10-17","arxiv_id":"2410.13691","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistically-grounded-analysis-of-language","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","date":"2024-10-17","arxiv_id":"2410.13396","n_code_links":0,"syntology":null},{"paper":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"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) · 0 unverified","official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metacognitive-monitoring-a-human-ability","title":"Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence","date":"2024-10-17","arxiv_id":"2410.13392","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","n_code_links":1,"syntology":null},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openmatch/rag-ddr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","n_code_links":1,"syntology":null},{"paper":null,"slug":"soullmate-an-application-enhancing-diverse","title":"SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques","date":"2024-10-17","arxiv_id":"2410.16322","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-compute-optimal-vision-transformers","title":"Training Compute-Optimal Vision Transformers for Brain Encoding","date":"2024-10-17","arxiv_id":"2410.19810","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-legal-knowledge-a-multilingual","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","date":"2024-10-17","arxiv_id":"2410.13456","n_code_links":0,"syntology":null},{"paper":"/paper/agent-skill-acquisition-for-large-language","slug":"agent-skill-acquisition-for-large-language","title":"Agent Skill Acquisition for Large Language Models via CycleQD","date":"2024-10-16","arxiv_id":"2410.14735","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["SakanaAI/CycleQD"],"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/at-rag-an-adaptive-rag-model-enhancing-query","slug":"at-rag-an-adaptive-rag-model-enhancing-query","title":"AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning","date":"2024-10-16","arxiv_id":"2410.12886","n_code_links":1,"syntology":null},{"paper":"/paper/cofe-rag-a-comprehensive-full-chain","slug":"cofe-rag-a-comprehensive-full-chain","title":"CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity","date":"2024-10-16","arxiv_id":"2410.12248","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-scaling-versus-task-scaling-in-in","title":"Context-Scaling versus Task-Scaling in In-Context Learning","date":"2024-10-16","arxiv_id":"2410.12783","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-attribution-bias-in-retrieval","title":"Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models","date":"2024-10-16","arxiv_id":"2410.12380","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-hate","title":"Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish","date":"2024-10-16","arxiv_id":"2410.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusionllm-a-decentralized-llm-training-system","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","date":"2024-10-16","arxiv_id":"2410.12707","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-semantic-chunking-worth-the-computational","title":"Is Semantic Chunking Worth the Computational Cost?","date":"2024-10-16","arxiv_id":"2410.13070","n_code_links":0,"syntology":null},{"paper":null,"slug":"kallini-et-al-2024-do-not-compare-impossible","title":"Kallini et al. (2024) do not compare impossible languages with constituency-based ones","date":"2024-10-16","arxiv_id":"2410.12271","n_code_links":0,"syntology":null},{"paper":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","slug":"mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","arxiv_id":"2410.13085","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["richard-peng-xia/mmed-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"shapefilegpt-a-multi-agent-large-language","title":"ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing","date":"2024-10-16","arxiv_id":"2410.12376","n_code_links":0,"syntology":null},{"paper":"/paper/stabilize-the-latent-space-for-image","slug":"stabilize-the-latent-space-for-image","title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","date":"2024-10-16","arxiv_id":"2410.12490","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["DAMO-NLP-SG/DiGIT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"table-llm-specialist-language-model","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","date":"2024-10-16","arxiv_id":"2410.12164","n_code_links":0,"syntology":null},{"paper":"/paper/unitary-multi-margin-bert-for-robust-natural","slug":"unitary-multi-margin-bert-for-robust-natural","title":"Unitary Multi-Margin BERT for Robust Natural Language Processing","date":"2024-10-16","arxiv_id":"2410.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","n_code_links":0,"syntology":null},{"paper":null,"slug":"athena-retrieval-augmented-legal-judgment","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","date":"2024-10-15","arxiv_id":"2410.11195","n_code_links":0,"syntology":null},{"paper":"/paper/deciphering-the-chaos-enhancing-jailbreak","slug":"deciphering-the-chaos-enhancing-jailbreak","title":"Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation","date":"2024-10-15","arxiv_id":"2410.11317","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qizhangli/adversarial-prompt-translator"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamicer-resolving-emerging-mentions-to","slug":"dynamicer-resolving-emerging-mentions-to","title":"DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG","date":"2024-10-15","arxiv_id":"2410.11494","n_code_links":1,"syntology":null},{"paper":null,"slug":"evidence-of-cognitive-deficits","title":"Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis","date":"2024-10-15","arxiv_id":"2410.11756","n_code_links":0,"syntology":null},{"paper":null,"slug":"holistic-reasoning-with-long-context-lms-a","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","date":"2024-10-15","arxiv_id":"2410.11996","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-hate-lost-in-translation-evaluation-of","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","date":"2024-10-15","arxiv_id":"2410.11230","n_code_links":0,"syntology":null},{"paper":"/paper/mtu-bench-a-multi-granularity-tool-use","slug":"mtu-bench-a-multi-granularity-tool-use","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11710","n_code_links":1,"syntology":null},{"paper":null,"slug":"nonlinear-gaussian-process-tomography-with","title":"Nonlinear Gaussian process tomography with imposed non-negativity constraints on physical quantities for plasma diagnostics","date":"2024-10-15","arxiv_id":"2410.11454","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-capacity-of-citation-generation-by","title":"On the Capacity of Citation Generation by Large Language Models","date":"2024-10-15","arxiv_id":"2410.11217","n_code_links":0,"syntology":null},{"paper":"/paper/pixology-probing-the-linguistic-and-visual","slug":"pixology-probing-the-linguistic-and-visual","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","date":"2024-10-15","arxiv_id":"2410.12011","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kushaltatariya/Pixology"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"redeep-detecting-hallucination-in-retrieval","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","date":"2024-10-15","arxiv_id":"2410.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","n_code_links":0,"syntology":null},{"paper":"/paper/rulerag-rule-guided-retrieval-augmented","slug":"rulerag-rule-guided-retrieval-augmented","title":"RuleRAG: Rule-guided retrieval-augmented generation with language models for question answering","date":"2024-10-15","arxiv_id":"2410.22353","n_code_links":1,"syntology":null},{"paper":null,"slug":"seer-self-aligned-evidence-extraction-for","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11315","n_code_links":0,"syntology":null},{"paper":"/paper/self-adaptive-multimodal-retrieval-augmented","slug":"self-adaptive-multimodal-retrieval-augmented","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11321","n_code_links":1,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","n_code_links":0,"syntology":null},{"paper":null,"slug":"sorted-weight-sectioning-for-energy-efficient","title":"Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars","date":"2024-10-15","arxiv_id":"2410.11298","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-interlocutors-experiments-with","title":"Synthetic Interlocutors. Experiments with Generative AI to Prolong Ethnographic Encounters","date":"2024-10-15","arxiv_id":"2410.11395","n_code_links":0,"syntology":null},{"paper":null,"slug":"telco-dpr-a-hybrid-dataset-for-evaluating","title":"Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications","date":"2024-10-15","arxiv_id":"2410.19790","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":"/paper/an-annotated-dataset-of-errors-in-premodern","slug":"an-annotated-dataset-of-errors-in-premodern","title":"An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them","date":"2024-10-14","arxiv_id":"2410.11071","n_code_links":1,"syntology":null},{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-rag-question-identification-and-answer","title":"Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations","date":"2024-10-14","arxiv_id":"2410.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-mixer-ya-nahi-novel-approaches-to","title":"Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities","date":"2024-10-14","arxiv_id":"2410.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"dissecting-embedding-method-learning-higher","title":"Dissecting embedding method: learning higher-order structures from data","date":"2024-10-14","arxiv_id":"2410.10917","n_code_links":0,"syntology":null},{"paper":"/paper/double-jeopardy-and-climate-impact-in-the-use","slug":"double-jeopardy-and-climate-impact-in-the-use","title":"Double Jeopardy and Climate Impact in the Use of Large Language Models: Socio-economic Disparities and Reduced Utility for Non-English Speakers","date":"2024-10-14","arxiv_id":"2410.10665","n_code_links":1,"syntology":null},{"paper":"/paper/easyrag-efficient-retrieval-augmented","slug":"easyrag-efficient-retrieval-augmented","title":"EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations","date":"2024-10-14","arxiv_id":"2410.10315","n_code_links":1,"syntology":null},{"paper":null,"slug":"funnelrag-a-coarse-to-fine-progressive","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","date":"2024-10-14","arxiv_id":"2410.10293","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-of-llm-in-economics-an","title":"Gender Bias of LLM in Economics: An Existentialism Perspective","date":"2024-10-14","arxiv_id":"2410.19775","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-records-boosting-retrieval-augmented","slug":"graph-of-records-boosting-retrieval-augmented","title":"Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs","date":"2024-10-14","arxiv_id":"2410.11001","n_code_links":1,"syntology":null},{"paper":"/paper/one-language-many-gaps-evaluating-dialect","slug":"one-language-many-gaps-evaluating-dialect","title":"One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","date":"2024-10-14","arxiv_id":"2410.11005","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fangru-lin/redial_dialect_robustness_fairness"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"performance-in-a-dialectal-profiling-task-of","title":"Performance in a dialectal profiling task of LLMs for varieties of Brazilian Portuguese","date":"2024-10-14","arxiv_id":"2410.10991","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-legal-judgement-prediction-in-a","slug":"rethinking-legal-judgement-prediction-in-a","title":"Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10542","n_code_links":1,"syntology":null},{"paper":"/paper/rocoft-efficient-finetuning-of-large-language","slug":"rocoft-efficient-finetuning-of-large-language","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","date":"2024-10-14","arxiv_id":"2410.10075","n_code_links":1,"syntology":null},{"paper":"/paper/sana-efficient-high-resolution-image","slug":"sana-efficient-high-resolution-image","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10629","n_code_links":2,"syntology":null},{"paper":null,"slug":"stackfeed-structured-textual-actor-critic","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","date":"2024-10-14","arxiv_id":"2410.10584","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-multi-head-attention-via","slug":"towards-better-multi-head-attention-via","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","date":"2024-10-14","arxiv_id":"2410.10914","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dashenzi721/csp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"c7bfc0ced6a0ac505d34caa5edea3a47034e627bed720011df63ed3286e4cf68","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}