{"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/17","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":17,"pages_in_order":109,"rows_per_page":100,"rows":[1601,1700],"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/16","next":"/method/attention-dropout/papers/18","papers":[{"paper":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-neural-network-interpretability-1","slug":"enhancing-neural-network-interpretability-1","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","date":"2024-11-02","arxiv_id":"2411.01220","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":["luke-marks0/mutual-feature-regularization"],"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":null,"slug":"attackqa-development-and-adoption-of-a","title":"AttackQA: Development and Adoption of a Dataset for Assisting Cybersecurity Operations using Fine-tuned and Open-Source LLMs","date":"2024-11-01","arxiv_id":"2411.01073","n_code_links":0,"syntology":null},{"paper":null,"slug":"corag-a-cost-constrained-retrieval","title":"CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation","date":"2024-11-01","arxiv_id":"2411.00744","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-lab-test-results-on","title":"Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes","date":"2024-11-01","arxiv_id":"2411.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-ref-enhancing-reference-handling-in","title":"LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models","date":"2024-11-01","arxiv_id":"2411.00294","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-a-game-changer-for-software-engineers","title":"LLMs: A Game-Changer for Software Engineers?","date":"2024-11-01","arxiv_id":"2411.00932","n_code_links":0,"syntology":null},{"paper":null,"slug":"provenance-a-light-weight-fact-checker-for","title":"Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output","date":"2024-11-01","arxiv_id":"2411.01022","n_code_links":0,"syntology":null},{"paper":"/paper/rationale-guided-retrieval-augmented","slug":"rationale-guided-retrieval-augmented","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","date":"2024-11-01","arxiv_id":"2411.00300","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":["dmis-lab/rag2"],"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":"towards-multi-source-retrieval-augmented","title":"Towards Multi-Source Retrieval-Augmented Generation via Synergizing Reasoning and Preference-Driven Retrieval","date":"2024-11-01","arxiv_id":"2411.00689","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-reducing-the-need-for-learning-rate","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","date":"2024-10-31","arxiv_id":"2410.23922","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-quantum-software-maintenance","title":"Automating Quantum Software Maintenance: Flakiness Detection and Root Cause Analysis","date":"2024-10-31","arxiv_id":"2410.23578","n_code_links":0,"syntology":null},{"paper":null,"slug":"judgerank-leveraging-large-language-models","title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","date":"2024-10-31","arxiv_id":"2411.00142","n_code_links":0,"syntology":null},{"paper":null,"slug":"leaf-learning-and-evaluation-augmented-by","title":"LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models","date":"2024-10-31","arxiv_id":"2410.23526","n_code_links":0,"syntology":null},{"paper":null,"slug":"responsible-retrieval-augmented-generation","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","date":"2024-10-31","arxiv_id":"2410.23902","n_code_links":0,"syntology":null},{"paper":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"a-comprehensive-study-on-quantization","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","date":"2024-10-30","arxiv_id":"2411.02530","n_code_links":0,"syntology":null},{"paper":"/paper/coral-benchmarking-multi-turn-conversational","slug":"coral-benchmarking-multi-turn-conversational","title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","date":"2024-10-30","arxiv_id":"2410.23090","n_code_links":1,"syntology":null},{"paper":null,"slug":"eliciting-critical-reasoning-in-retrieval","title":"Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations","date":"2024-10-30","arxiv_id":"2410.22874","n_code_links":0,"syntology":null},{"paper":"/paper/emotional-rag-enhancing-role-playing-agents","slug":"emotional-rag-enhancing-role-playing-agents","title":"Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval","date":"2024-10-30","arxiv_id":"2410.23041","n_code_links":1,"syntology":null},{"paper":null,"slug":"hijackrag-hijacking-attacks-against-retrieval","title":"HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models","date":"2024-10-30","arxiv_id":"2410.22832","n_code_links":0,"syntology":null},{"paper":"/paper/protransformer-robustify-transformers-via","slug":"protransformer-robustify-transformers-via","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","date":"2024-10-30","arxiv_id":"2410.23182","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-with","title":"Retrieval-Augmented Generation with Estimation of Source Reliability","date":"2024-10-30","arxiv_id":"2410.22954","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-enrichment-of-the-quantum-cascade","slug":"semantic-enrichment-of-the-quantum-cascade","title":"Semantic Enrichment of the Quantum Cascade Laser Properties in Text- A Knowledge Graph Generation Approach","date":"2024-10-30","arxiv_id":"2410.22996","n_code_links":1,"syntology":null},{"paper":null,"slug":"textsc-long-2-rag-evaluating-long-context","title":"Long$^2$RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall","date":"2024-10-30","arxiv_id":"2410.23000","n_code_links":0,"syntology":null},{"paper":"/paper/abrupt-learning-in-transformers-a-case-study","slug":"abrupt-learning-in-transformers-a-case-study","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","date":"2024-10-29","arxiv_id":"2410.22244","n_code_links":0,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/beyond-text-optimizing-rag-with-multimodal","slug":"beyond-text-optimizing-rag-with-multimodal","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","date":"2024-10-29","arxiv_id":"2410.21943","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":0,"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":["riedlerm/multimodal_rag_for_industry"],"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":null,"slug":"cfsafety-comprehensive-fine-grained-safety","title":"CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs","date":"2024-10-29","arxiv_id":"2410.21695","n_code_links":0,"syntology":null},{"paper":null,"slug":"coupling-quantum-like-cognition-with-the","title":"Coupling quantum-like cognition with the neuronal networks within generalized probability theory","date":"2024-10-29","arxiv_id":"2411.00036","n_code_links":0,"syntology":null},{"paper":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-learning-adaptable-foundation-models","title":"Meta-Learning Adaptable Foundation Models","date":"2024-10-29","arxiv_id":"2410.22264","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-choice-in-ordered-bundles","title":"Sequential choice in ordered bundles","date":"2024-10-29","arxiv_id":"2410.21670","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-yet-effective-corpus-construction-1","slug":"a-simple-yet-effective-corpus-construction-1","title":"A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction","date":"2024-10-28","arxiv_id":"2410.20838","n_code_links":1,"syntology":null},{"paper":"/paper/autorag-automated-framework-for-optimization","slug":"autorag-automated-framework-for-optimization","title":"AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline","date":"2024-10-28","arxiv_id":"2410.20878","n_code_links":2,"syntology":null},{"paper":null,"slug":"banditcat-and-autoirt-machine-learning","title":"BanditCAT and AutoIRT: Machine Learning Approaches to Computerized Adaptive Testing and Item Calibration","date":"2024-10-28","arxiv_id":"2410.21033","n_code_links":0,"syntology":null},{"paper":"/paper/blast-block-level-adaptive-structured","slug":"blast-block-level-adaptive-structured","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","date":"2024-10-28","arxiv_id":"2410.21262","n_code_links":1,"syntology":null},{"paper":null,"slug":"calibrated-decision-making-through-llm","title":"Calibrated Decision-Making through LLM-Assisted Retrieval","date":"2024-10-28","arxiv_id":"2411.08891","n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-interventions-on-causal-paths-mapping","title":"Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics","date":"2024-10-28","arxiv_id":"2410.21353","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-domain-specific-models-and-llms-for","title":"Combining Domain-Specific Models and LLMs for Automated Disease Phenotyping from Survey Data","date":"2024-10-28","arxiv_id":"2410.20695","n_code_links":0,"syntology":null},{"paper":null,"slug":"crat-a-multi-agent-framework-for-causality","title":"CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Models","date":"2024-10-28","arxiv_id":"2410.21067","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-medical-text-processing","title":"Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study","date":"2024-10-28","arxiv_id":"2410.20792","n_code_links":0,"syntology":null},{"paper":null,"slug":"embedding-with-large-language-models-for","title":"Embedding with Large Language Models for Classification of HIPAA Safeguard Compliance Rules","date":"2024-10-28","arxiv_id":"2410.20664","n_code_links":0,"syntology":null},{"paper":"/paper/geo-fub-a-method-for-constructing-an-operator","slug":"geo-fub-a-method-for-constructing-an-operator","title":"Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models","date":"2024-10-28","arxiv_id":"2410.20975","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-4-less-politically-biased-than-gpt-3-5","title":"Is GPT-4 Less Politically Biased than GPT-3.5? A Renewed Investigation of ChatGPT's Political Biases","date":"2024-10-28","arxiv_id":"2410.21008","n_code_links":0,"syntology":null},{"paper":"/paper/kd-lora-a-hybrid-approach-to-efficient-fine","slug":"kd-lora-a-hybrid-approach-to-efficient-fine","title":"KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation","date":"2024-10-28","arxiv_id":"2410.20777","n_code_links":1,"syntology":null},{"paper":null,"slug":"linformer-a-linear-based-lightweight","title":"LinFormer: A Linear-based Lightweight Transformer Architecture For Time-Aware MIMO Channel Prediction","date":"2024-10-28","arxiv_id":"2410.21351","n_code_links":0,"syntology":null},{"paper":"/paper/llms-are-biased-evaluators-but-not-biased-for","slug":"llms-are-biased-evaluators-but-not-biased-for","title":"LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation","date":"2024-10-28","arxiv_id":"2410.20833","n_code_links":1,"syntology":null},{"paper":"/paper/multitok-variable-length-tokenization-for","slug":"multitok-variable-length-tokenization-for","title":"MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression","date":"2024-10-28","arxiv_id":"2410.21548","n_code_links":1,"syntology":null},{"paper":null,"slug":"plan-times-rag-planning-guided-retrieval","title":"Plan$\\times$RAG: Planning-guided Retrieval Augmented Generation","date":"2024-10-28","arxiv_id":"2410.20753","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-search-evaluation","title":"Semantic Search Evaluation","date":"2024-10-28","arxiv_id":"2410.21549","n_code_links":0,"syntology":null},{"paper":"/paper/simple-is-effective-the-roles-of-graphs-and","slug":"simple-is-effective-the-roles-of-graphs-and","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","date":"2024-10-28","arxiv_id":"2410.20724","n_code_links":1,"syntology":{"ran":9,"of":15,"n_ran_checked":9,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["graph-com/subgraphrag"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"stealthy-jailbreak-attacks-on-large-language","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","date":"2024-10-28","arxiv_id":"2410.21083","n_code_links":0,"syntology":null},{"paper":"/paper/uottawa-at-legallens-2024-transformer-based","slug":"uottawa-at-legallens-2024-transformer-based","title":"uOttawa at LegalLens-2024: Transformer-based Classification Experiments","date":"2024-10-28","arxiv_id":"2410.21139","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-based-dense-retrieval-a","title":"Deep Learning Based Dense Retrieval: A Comparative Study","date":"2024-10-27","arxiv_id":"2410.20315","n_code_links":0,"syntology":null},{"paper":"/paper/llm-robustness-against-misinformation-in","slug":"llm-robustness-against-misinformation-in","title":"LLM Robustness Against Misinformation in Biomedical Question Answering","date":"2024-10-27","arxiv_id":"2410.21330","n_code_links":1,"syntology":null},{"paper":null,"slug":"r-3ag-first-workshop-on-refined-and-reliable","title":"R^3AG: First Workshop on Refined and Reliable Retrieval Augmented Generation","date":"2024-10-27","arxiv_id":"2410.20598","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","n_code_links":1,"syntology":null},{"paper":null,"slug":"mask-based-membership-inference-attacks-for","title":"Mask-based Membership Inference Attacks for Retrieval-Augmented Generation","date":"2024-10-26","arxiv_id":"2410.20142","n_code_links":0,"syntology":null},{"paper":null,"slug":"think-carefully-and-check-again-meta","title":"Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization","date":"2024-10-26","arxiv_id":"2410.20021","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-tutorial-on-teaching-data-analytics-with","title":"A Tutorial on Teaching Data Analytics with Generative AI","date":"2024-10-25","arxiv_id":"2411.07244","n_code_links":0,"syntology":null},{"paper":null,"slug":"chunkrag-novel-llm-chunk-filtering-method-for","title":"ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems","date":"2024-10-25","arxiv_id":"2410.19572","n_code_links":0,"syntology":null},{"paper":null,"slug":"fishnet-financial-intelligence-from-sub","title":"FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning","date":"2024-10-25","arxiv_id":"2410.19727","n_code_links":0,"syntology":null},{"paper":"/paper/geollava-efficient-fine-tuned-vision-language","slug":"geollava-efficient-fine-tuned-vision-language","title":"GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing","date":"2024-10-25","arxiv_id":"2410.19552","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["HosamGen/GeoLLaVA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"integrating-large-language-models-with-2","title":"Integrating Large Language Models with Internet of Things Applications","date":"2024-10-25","arxiv_id":"2410.19223","n_code_links":0,"syntology":null},{"paper":null,"slug":"bielik-7b-v0-1-a-polish-language-model","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","date":"2024-10-24","arxiv_id":"2410.18565","n_code_links":0,"syntology":null},{"paper":"/paper/difficult-for-whom-a-study-of-japanese","slug":"difficult-for-whom-a-study-of-japanese","title":"Difficult for Whom? A Study of Japanese Lexical Complexity","date":"2024-10-24","arxiv_id":"2410.18567","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-self-tuning-llms-for-enhanced","slug":"iterative-self-tuning-llms-for-enhanced","title":"Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities","date":"2024-10-24","arxiv_id":"2410.18469","n_code_links":1,"syntology":null},{"paper":"/paper/little-giants-synthesizing-high-quality","slug":"little-giants-synthesizing-high-quality","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","date":"2024-10-24","arxiv_id":"2410.18634","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["haon-chen/SPEED"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/pdl-a-declarative-prompt-programming-language","slug":"pdl-a-declarative-prompt-programming-language","title":"PDL: A Declarative Prompt Programming Language","date":"2024-10-24","arxiv_id":"2410.19135","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-ranking-llms-mechanistic","title":"Understanding Ranking LLMs: A Mechanistic Analysis for Information Retrieval","date":"2024-10-24","arxiv_id":"2410.18527","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-gsai/smdm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"understanding-players-as-if-they-are-talking","title":"Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study","date":"2024-10-24","arxiv_id":"2410.18605","n_code_links":0,"syntology":null},{"paper":"/paper/an-adaptive-framework-for-generating","slug":"an-adaptive-framework-for-generating","title":"An Adaptive Framework for Generating Systematic Explanatory Answer in Online Q&A Platforms","date":"2024-10-23","arxiv_id":"2410.17694","n_code_links":1,"syntology":null},{"paper":"/paper/differentially-private-learning-needs-better","slug":"differentially-private-learning-needs-better","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","date":"2024-10-23","arxiv_id":"2410.17566","n_code_links":1,"syntology":null},{"paper":null,"slug":"future-token-prediction-causal-language","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","date":"2024-10-23","arxiv_id":"2410.18160","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-the-domain-adaptation-of-retrieval","title":"Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination","date":"2024-10-23","arxiv_id":"2410.17783","n_code_links":0,"syntology":null},{"paper":null,"slug":"locating-information-in-large-language-models","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","date":"2024-10-23","arxiv_id":"2410.17770","n_code_links":0,"syntology":null},{"paper":"/paper/longrag-a-dual-perspective-retrieval","slug":"longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","arxiv_id":"2410.18050","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"phrase":"8 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qingfei1/longrag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mcubert-memory-efficient-bert-inference-on","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","date":"2024-10-23","arxiv_id":"2410.17957","n_code_links":0,"syntology":null},{"paper":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","n_code_links":1,"syntology":null},{"paper":null,"slug":"simrag-self-improving-retrieval-augmented","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","date":"2024-10-23","arxiv_id":"2410.17952","n_code_links":0,"syntology":null},{"paper":"/paper/dhoroni-exploring-bengali-climate-change-and","slug":"dhoroni-exploring-bengali-climate-change-and","title":"Dhoroni: Exploring Bengali Climate Change and Environmental Views with a Multi-Perspective News Dataset and Natural Language Processing","date":"2024-10-22","arxiv_id":"2410.17225","n_code_links":1,"syntology":null},{"paper":null,"slug":"distill-synthkg-distilling-knowledge-graph","title":"Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency","date":"2024-10-22","arxiv_id":"2410.16597","n_code_links":0,"syntology":null},{"paper":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","n_code_links":1,"syntology":null},{"paper":null,"slug":"scattered-forest-search-smarter-code-space","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","date":"2024-10-22","arxiv_id":"2411.05010","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartrag-jointly-learn-rag-related-tasks-from","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","date":"2024-10-22","arxiv_id":"2410.18141","n_code_links":0,"syntology":null},{"paper":"/paper/tracing-the-development-of-the-virtual","slug":"tracing-the-development-of-the-virtual","title":"Tracing the Development of the Virtual Particle Concept Using Semantic Change Detection","date":"2024-10-22","arxiv_id":"2410.16855","n_code_links":1,"syntology":null},{"paper":"/paper/an-efficient-system-for-automatic-map","slug":"an-efficient-system-for-automatic-map","title":"An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps","date":"2024-10-21","arxiv_id":"2410.15780","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-and-data-augmentation-for","slug":"deep-learning-and-data-augmentation-for","title":"Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt","date":"2024-10-21","arxiv_id":"2410.15804","n_code_links":1,"syntology":null},{"paper":"/paper/developing-retrieval-augmented-generation-rag","slug":"developing-retrieval-augmented-generation-rag","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","date":"2024-10-21","arxiv_id":"2410.15944","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-pretraining-via-active-forgetting","title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","date":"2024-10-21","arxiv_id":"2410.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"guardians-of-discourse-evaluating-llms-on","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","date":"2024-10-21","arxiv_id":"2410.15623","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neuron-level-interpretability-with","title":"Improving Neuron-level Interpretability with White-box Language Models","date":"2024-10-21","arxiv_id":"2410.16443","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-retrieval-augmented-generation-for","title":"Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions","date":"2024-10-21","arxiv_id":"2410.15572","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightfusionrec-lightweight-transformers-based","title":"LightFusionRec: Lightweight Transformers-Based Cross-Domain Recommendation Model","date":"2024-10-21","arxiv_id":"2410.15656","n_code_links":0,"syntology":null},{"paper":"/paper/natural-galore-accelerating-galore-for-memory","slug":"natural-galore-accelerating-galore-for-memory","title":"Natural GaLore: Accelerating GaLore for memory-efficient LLM Training and Fine-tuning","date":"2024-10-21","arxiv_id":"2410.16029","n_code_links":1,"syntology":null},{"paper":"/paper/on-creating-an-english-thai-code-switched","slug":"on-creating-an-english-thai-code-switched","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","date":"2024-10-21","arxiv_id":"2410.16221","n_code_links":1,"syntology":null},{"paper":null,"slug":"rag4itops-a-supervised-fine-tunable-and","title":"RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance","date":"2024-10-21","arxiv_id":"2410.15805","n_code_links":0,"syntology":null}],"record_sha256":"004264d30c00976f3320144666da6d99f60fc236d2b29c00bd6fffeaf115e193","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}