{"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/weight-decay/papers/23","list_of":"/method/weight-decay","method":"Weight Decay","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":23,"pages_in_order":108,"rows_per_page":100,"rows":[2201,2300],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"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/weight-decay","prev":"/method/weight-decay/papers/22","next":"/method/weight-decay/papers/24","papers":[{"paper":null,"slug":"tagify-llm-powered-tagging-interface-for","title":"TAGIFY: LLM-powered Tagging Interface for Improved Data Findability on OGD portals","date":"2024-07-26","arxiv_id":"2407.18764","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-cross-environment-hyperparameter-setting","title":"The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning","date":"2024-07-26","arxiv_id":"2407.18840","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-the","title":"Using Large Language Models for the Interpretation of Building Regulations","date":"2024-07-26","arxiv_id":"2407.21060","n_code_links":0,"syntology":null},{"paper":null,"slug":"banyan-improved-representation-learning-with","title":"Banyan: Improved Representation Learning with Explicit Structure","date":"2024-07-25","arxiv_id":"2407.17771","n_code_links":0,"syntology":null},{"paper":null,"slug":"closing-the-gap-between-open-source-and","title":"Closing the gap between open-source and commercial large language models for medical evidence summarization","date":"2024-07-25","arxiv_id":"2408.00588","n_code_links":0,"syntology":null},{"paper":"/paper/cost-effective-instruction-learning-for","slug":"cost-effective-instruction-learning-for","title":"Cost-effective Instruction Learning for Pathology Vision and Language Analysis","date":"2024-07-25","arxiv_id":"2407.17734","n_code_links":1,"syntology":null},{"paper":"/paper/peft-u-parameter-efficient-fine-tuning-for","slug":"peft-u-parameter-efficient-fine-tuning-for","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","date":"2024-07-25","arxiv_id":"2407.18078","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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":["ChrisIsKing/Parameter-Efficient-Personalization"],"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":"/paper/personagym-evaluating-persona-agents-and-llms","slug":"personagym-evaluating-persona-agents-and-llms","title":"PersonaGym: Evaluating Persona Agents and LLMs","date":"2024-07-25","arxiv_id":"2407.18416","n_code_links":1,"syntology":null},{"paper":null,"slug":"roberta-resnext-and-bilstm-with-self","title":"RoBERTa, ResNeXt and BiLSTM with self-attention: The ultimate trio for customer sentiment analysis","date":"2024-07-25","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geometry-of-queries-query-based","title":"The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation","date":"2024-07-25","arxiv_id":"2407.18044","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-interplay-of-scale-data-and","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","date":"2024-07-25","arxiv_id":"2407.21058","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21056","title":"What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers","date":"2024-07-24","arxiv_id":"2407.21056","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-approach-to-misspelling","title":"A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance","date":"2024-07-24","arxiv_id":"2407.17383","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-two-step-fine-tuning-pipeline-for","title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks","date":"2024-07-24","arxiv_id":"2407.17284","n_code_links":0,"syntology":null},{"paper":null,"slug":"bailicai-a-domain-optimized-retrieval","title":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","date":"2024-07-24","arxiv_id":"2407.21055","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-large-language-models-on-driving","title":"Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous Vehicles","date":"2024-07-24","arxiv_id":"2407.17211","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-polysemy-evolution-using","title":"Analyzing Polysemy Evolution Using Semantic Cells","date":"2024-07-23","arxiv_id":"2407.16110","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-intelligence-in-extracting","title":"Artificial Intelligence in Extracting Diagnostic Data from Dental Records","date":"2024-07-23","arxiv_id":"2407.21050","n_code_links":0,"syntology":null},{"paper":"/paper/data-mixture-inference-what-do-bpe-tokenizers","slug":"data-mixture-inference-what-do-bpe-tokenizers","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","date":"2024-07-23","arxiv_id":"2407.16607","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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alisawuffles/tokenizer-attack"],"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/enhancing-llm-s-cognition-via-structurization","slug":"enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","arxiv_id":"2407.16434","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":["alibaba/struxgpt"],"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":"lawluo-a-chinese-law-firm-co-run-by-llm","title":"LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation","date":"2024-07-23","arxiv_id":"2407.16252","n_code_links":0,"syntology":null},{"paper":"/paper/patched-rtc-evaluating-llms-for-diverse","slug":"patched-rtc-evaluating-llms-for-diverse","title":"Patched RTC: evaluating LLMs for diverse software development tasks","date":"2024-07-23","arxiv_id":"2407.16557","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-or-long","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","date":"2024-07-23","arxiv_id":"2407.16833","n_code_links":0,"syntology":null},{"paper":"/paper/robust-privacy-amidst-innovation-with-large","slug":"robust-privacy-amidst-innovation-with-large","title":"Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks","date":"2024-07-23","arxiv_id":"2407.16166","n_code_links":1,"syntology":null},{"paper":null,"slug":"tookabert-a-step-forward-for-persian-nlu","title":"TookaBERT: A Step Forward for Persian NLU","date":"2024-07-23","arxiv_id":"2407.16382","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-comparison-of-video-frame","title":"An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval","date":"2024-07-22","arxiv_id":"2408.03340","n_code_links":0,"syntology":null},{"paper":null,"slug":"customized-retrieval-augmented-generation-and","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","date":"2024-07-22","arxiv_id":"2407.15353","n_code_links":0,"syntology":null},{"paper":null,"slug":"impacts-of-anthropomorphizing-large-language","title":"Impacts of Anthropomorphizing Large Language Models in Learning Environments","date":"2024-07-22","arxiv_id":"2408.03945","n_code_links":0,"syntology":null},{"paper":null,"slug":"imposter-ai-adversarial-attacks-with-hidden","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","date":"2024-07-22","arxiv_id":"2407.15399","n_code_links":0,"syntology":null},{"paper":"/paper/inverted-activations","slug":"inverted-activations","title":"Inverted Activations: Reducing Memory Footprint in Neural Network Training","date":"2024-07-22","arxiv_id":"2407.15545","n_code_links":1,"syntology":null},{"paper":"/paper/llmmap-fingerprinting-for-large-language","slug":"llmmap-fingerprinting-for-large-language","title":"LLMmap: Fingerprinting For Large Language Models","date":"2024-07-22","arxiv_id":"2407.15847","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"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) · 7 unverified","official":{"repos":["pasquini-dario/LLMmap"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/mminstruct-a-high-quality-multi-modal","slug":"mminstruct-a-high-quality-multi-modal","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","date":"2024-07-22","arxiv_id":"2407.15838","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuecao0119/mminstruct"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"morse-bridging-the-gap-in-cybersecurity","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","date":"2024-07-22","arxiv_id":"2407.15748","n_code_links":0,"syntology":null},{"paper":"/paper/radiorag-factual-large-language-models-for","slug":"radiorag-factual-large-language-models-for","title":"RadioRAG: Factual large language models for enhanced diagnostics in radiology using online retrieval augmented generation","date":"2024-07-22","arxiv_id":"2407.15621","n_code_links":1,"syntology":null},{"paper":"/paper/stretching-each-dollar-diffusion-training","slug":"stretching-each-dollar-diffusion-training","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","date":"2024-07-22","arxiv_id":"2407.15811","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["sonyresearch/micro_diffusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unlocking-the-potential-benchmarking-large","title":"Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research","date":"2024-07-22","arxiv_id":"2407.21045","n_code_links":0,"syntology":null},{"paper":null,"slug":"zzu-nlp-at-sighan-2024-dimabsa-task-aspect","title":"ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning","date":"2024-07-22","arxiv_id":"2407.15341","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-level-multi-label-text-classification","title":"A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts","date":"2024-07-21","arxiv_id":"2407.15136","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-00798","title":"Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base","date":"2024-07-20","arxiv_id":"2408.00798","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-generation-of-fashion-images-using","slug":"automatic-generation-of-fashion-images-using","title":"Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models","date":"2024-07-20","arxiv_id":"2407.14944","n_code_links":1,"syntology":null},{"paper":null,"slug":"differential-privacy-of-cross-attention-with","title":"Differential Privacy of Cross-Attention with Provable Guarantee","date":"2024-07-20","arxiv_id":"2407.14717","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-databases-improve-success-in","title":"Adversarial Databases Improve Success in Retrieval-based Large Language Models","date":"2024-07-19","arxiv_id":"2407.14609","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatqa-2-bridging-the-gap-to-proprietary-llms","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","date":"2024-07-19","arxiv_id":"2407.14482","n_code_links":0,"syntology":null},{"paper":"/paper/conditioning-chat-gpt-for-information","slug":"conditioning-chat-gpt-for-information","title":"Unipa-GPT: Large Language Models for university-oriented QA in Italian","date":"2024-07-19","arxiv_id":"2407.14246","n_code_links":1,"syntology":null},{"paper":null,"slug":"sqlfuse-enhancing-text-to-sql-performance","title":"SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy","date":"2024-07-19","arxiv_id":"2407.14568","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"black-box-opinion-manipulation-attacks-to","title":"Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-07-18","arxiv_id":"2407.13757","n_code_links":0,"syntology":null},{"paper":"/paper/can-open-source-llms-compete-with-commercial","slug":"can-open-source-llms-compete-with-commercial","title":"Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2024-07-18","arxiv_id":"2407.13511","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-for-anxiety","slug":"evaluating-large-language-models-for-anxiety","title":"Evaluating Large Language Models for Anxiety and Depression Classification using Counseling and Psychotherapy Transcripts","date":"2024-07-18","arxiv_id":"2407.13228","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-reliable-knowledge","title":"How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency","date":"2024-07-18","arxiv_id":"2407.13578","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-mistakes-prompting-for","title":"Learning-From-Mistakes Prompting for Indigenous Language Translation","date":"2024-07-18","arxiv_id":"2407.13343","n_code_links":0,"syntology":null},{"paper":null,"slug":"pragyan-connecting-the-dots-in-tweets","title":"PRAGyan -- Connecting the Dots in Tweets","date":"2024-07-18","arxiv_id":"2407.13909","n_code_links":0,"syntology":null},{"paper":null,"slug":"qalam-a-multimodal-llm-for-arabic-optical","title":"Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","date":"2024-07-18","arxiv_id":"2407.13559","n_code_links":0,"syntology":null},{"paper":"/paper/reconfigurable-intelligent-surface-aided-21","slug":"reconfigurable-intelligent-surface-aided-21","title":"Reconfigurable Intelligent Surface Aided Vehicular Edge Computing: Joint Phase-shift Optimization and Multi-User Power Allocation","date":"2024-07-18","arxiv_id":"2407.13123","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstruct-the-pruned-model-without-any","title":"Reconstruct the Pruned Model without Any Retraining","date":"2024-07-18","arxiv_id":"2407.13331","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-for-natural","title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","date":"2024-07-18","arxiv_id":"2407.13193","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieve-summarize-plan-advancing-multi-hop","title":"Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach","date":"2024-07-18","arxiv_id":"2407.13101","n_code_links":0,"syntology":null},{"paper":"/paper/werewolf-arena-a-case-study-in-llm-evaluation","slug":"werewolf-arena-a-case-study-in-llm-evaluation","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","date":"2024-07-18","arxiv_id":"2407.13943","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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":["google/werewolf_arena"],"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/agentpoison-red-teaming-llm-agents-via","slug":"agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","arxiv_id":"2407.12784","n_code_links":1,"syntology":{"ran":16,"of":19,"n_ran_checked":15,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["BillChan226/AgentPoison"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-learning-based-sentiment-analysis-of-1","title":"Deep Learning-based Sentiment Analysis of Olympics Tweets","date":"2024-07-17","arxiv_id":"2407.12376","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-initializing-transformers-with-pre-trained","title":"On Initializing Transformers with Pre-trained Embeddings","date":"2024-07-17","arxiv_id":"2407.12514","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-query-generation-for-enhanced","title":"Optimizing Query Generation for Enhanced Document Retrieval in RAG","date":"2024-07-17","arxiv_id":"2407.12325","n_code_links":0,"syntology":null},{"paper":"/paper/search-engines-llms-or-both-evaluating","slug":"search-engines-llms-or-both-evaluating","title":"Evaluating Search Engines and Large Language Models for Answering Health Questions","date":"2024-07-17","arxiv_id":"2407.12468","n_code_links":1,"syntology":null},{"paper":"/paper/sharif-str-at-semeval-2024-task-1-transformer","slug":"sharif-str-at-semeval-2024-task-1-transformer","title":"Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations","date":"2024-07-17","arxiv_id":"2407.12426","n_code_links":1,"syntology":null},{"paper":"/paper/text-and-feature-based-models-for-compound","slug":"text-and-feature-based-models-for-compound","title":"Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild","date":"2024-07-17","arxiv_id":"2407.12927","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"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":["nicolas-richet/feature-vs-text-compound-emotion"],"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":"/paper/better-rag-using-relevant-information-gain","slug":"better-rag-using-relevant-information-gain","title":"Better RAG using Relevant Information Gain","date":"2024-07-16","arxiv_id":"2407.12101","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-binary-multiclass-paraphasia-detection","title":"Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models","date":"2024-07-16","arxiv_id":"2407.11345","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbcg-can-ai-read-your-slide-deck","title":"ChatBCG: Can AI Read Your Slide Deck?","date":"2024-07-16","arxiv_id":"2407.12875","n_code_links":0,"syntology":null},{"paper":"/paper/does-refusal-training-in-llms-generalize-to","slug":"does-refusal-training-in-llms-generalize-to","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","date":"2024-07-16","arxiv_id":"2407.11969","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/llm-past-tense"],"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":null,"slug":"gpt-assisted-annotation-of-rhetorical-and","title":"GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text","date":"2024-07-16","arxiv_id":"2407.11827","n_code_links":0,"syntology":null},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-as-misleading","title":"Large Language Models as Misleading Assistants in Conversation","date":"2024-07-16","arxiv_id":"2407.11789","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-visual-language-models-are-also-good","title":"Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection","date":"2024-07-16","arxiv_id":"2407.12879","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-in-the-loop-part-1-expert-small-ai","title":"LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation","date":"2024-07-16","arxiv_id":"2407.12126","n_code_links":0,"syntology":null},{"paper":null,"slug":"mindful-rag-a-study-of-points-of-failure-in","title":"Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation","date":"2024-07-16","arxiv_id":"2407.12216","n_code_links":0,"syntology":null},{"paper":null,"slug":"r-sfllm-jamming-resilient-framework-for-split","title":"R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models","date":"2024-07-16","arxiv_id":"2407.11654","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-bias-in-political-sample","title":"Representation Bias in Political Sample Simulations with Large Language Models","date":"2024-07-16","arxiv_id":"2407.11409","n_code_links":0,"syntology":null},{"paper":null,"slug":"review-feedback-reason-refer-a-novel","title":"ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models","date":"2024-07-16","arxiv_id":"2407.12877","n_code_links":0,"syntology":null},{"paper":"/paper/scientific-qa-system-with-verifiable-answers","slug":"scientific-qa-system-with-verifiable-answers","title":"Scientific QA System with Verifiable Answers","date":"2024-07-16","arxiv_id":"2407.11485","n_code_links":1,"syntology":null},{"paper":"/paper/trust-no-bot-discovering-personal-disclosures","slug":"trust-no-bot-discovering-personal-disclosures","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","date":"2024-07-16","arxiv_id":"2407.11438","n_code_links":1,"syntology":null},{"paper":"/paper/communication-and-computation-efficient","slug":"communication-and-computation-efficient","title":"Communication- and Computation-Efficient Distributed Submodular Optimization in Robot Mesh Networks","date":"2024-07-15","arxiv_id":"2407.10382","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-based-operators-for","title":"Deep Learning-Based Operators for Evolutionary Algorithms","date":"2024-07-15","arxiv_id":"2407.10477","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-llms-for-verilog-generation","title":"CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization","date":"2024-07-15","arxiv_id":"2407.10424","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-retrieval-and-managing-retrieval-a","slug":"enhancing-retrieval-and-managing-retrieval-a","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","date":"2024-07-15","arxiv_id":"2407.10670","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ancientshi/erm4"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluation-of-rag-metrics-for-question","title":"Evaluation of RAG Metrics for Question Answering in the Telecom Domain","date":"2024-07-15","arxiv_id":"2407.12873","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-llm-respondents-for-item","title":"Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis","date":"2024-07-15","arxiv_id":"2407.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-new-connections-llms-as-puzzle","title":"Making New Connections: LLMs as Puzzle Generators for The New York Times' Connections Word Game","date":"2024-07-15","arxiv_id":"2407.11240","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-interpretability-of-large","title":"Mechanistic interpretability of large language models with applications to the financial services industry","date":"2024-07-15","arxiv_id":"2407.11215","n_code_links":0,"syntology":null},{"paper":"/paper/metallm-a-high-performant-and-cost-efficient","slug":"metallm-a-high-performant-and-cost-efficient","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","date":"2024-07-15","arxiv_id":"2407.10834","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mail-research/metallm-wrapper"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/texttt-mixgr-enhancing-retriever","slug":"texttt-mixgr-enhancing-retriever","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","date":"2024-07-15","arxiv_id":"2407.10691","n_code_links":1,"syntology":null},{"paper":"/paper/think-on-graph-2-0-deep-and-interpretable","slug":"think-on-graph-2-0-deep-and-interpretable","title":"Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation","date":"2024-07-15","arxiv_id":"2407.10805","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":13,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["idea-finai/tog-2"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"curriculum-learning-for-small-code-language","title":"Curriculum Learning for Small Code Language Models","date":"2024-07-14","arxiv_id":"2407.10194","n_code_links":0,"syntology":null},{"paper":null,"slug":"causality-extraction-from-medical-text-using","title":"Causality extraction from medical text using Large Language Models (LLMs)","date":"2024-07-13","arxiv_id":"2407.10020","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-with-symmetric-1","title":"Deep reinforcement learning with symmetric data augmentation applied for aircraft lateral attitude tracking control","date":"2024-07-13","arxiv_id":"2407.11077","n_code_links":0,"syntology":null},{"paper":null,"slug":"document-level-clinical-entity-and-relation","title":"Document-level Clinical Entity and Relation Extraction via Knowledge Base-Guided Generation","date":"2024-07-13","arxiv_id":"2407.10021","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-in-store-customer-journeys-from","title":"Generating In-store Customer Journeys from Scratch with GPT Architectures","date":"2024-07-13","arxiv_id":"2407.11081","n_code_links":0,"syntology":null},{"paper":"/paper/hydra-bidirectional-state-space-models","slug":"hydra-bidirectional-state-space-models","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","date":"2024-07-13","arxiv_id":"2407.09941","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":9,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["goombalab/hydra"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"resource-management-for-low-latency","title":"Resource Management for Low-latency Cooperative Fine-tuning of Foundation Models at the Network Edge","date":"2024-07-13","arxiv_id":"2407.09873","n_code_links":0,"syntology":null},{"paper":"/paper/astprompter-weakly-supervised-automated","slug":"astprompter-weakly-supervised-automated","title":"ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts","date":"2024-07-12","arxiv_id":"2407.09447","n_code_links":1,"syntology":null}],"record_sha256":"ced545d3ccd313abc85b2ef2234e42fd4c2fdcbc32243dee36516559742f36c9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}