{"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/gpt-4/papers/3","list_of":"/method/gpt-4","method":"GPT-4","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":3,"pages_in_order":29,"rows_per_page":100,"rows":[201,300],"of":2870,"counts":{"archive_papers_tagged":2870,"with_a_code_link":1244,"where_syntology_ran_a_sample":526,"not_listed_spam_title":0,"listed":2870,"listed_where_code_ran":526,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":417,"every_run_a_failure_of_syntologys_instrument":109,"listed_with_a_run_with_no_instrument_failure":417,"listed_every_run_a_failure_of_syntologys_instrument":109,"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/gpt-4","prev":"/method/gpt-4/papers/2","next":"/method/gpt-4/papers/4","papers":[{"paper":null,"slug":"response-benchmarking-the-ability-of-language","title":"RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation","date":"2025-03-14","arxiv_id":"2503.11348","n_code_links":0,"syntology":null},{"paper":"/paper/a-frustratingly-simple-yet-highly-effective","slug":"a-frustratingly-simple-yet-highly-effective","title":"A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1","date":"2025-03-13","arxiv_id":"2503.10635","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":["vila-lab/m-attack"],"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":"advanced-tool-learning-and-selection-system","title":"Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM","date":"2025-03-13","arxiv_id":"2503.10071","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-encounters-morphing-attack-detection","title":"ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models","date":"2025-03-13","arxiv_id":"2503.10937","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-i-look-like-a-cat-n-01-to-you-a-taxonomy","title":"Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark","date":"2025-03-13","arxiv_id":"2503.10357","n_code_links":0,"syntology":null},{"paper":null,"slug":"siege-autonomous-multi-turn-jailbreaking-of","title":"Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search","date":"2025-03-13","arxiv_id":"2503.10619","n_code_links":0,"syntology":null},{"paper":"/paper/agentdam-privacy-leakage-evaluation-for","slug":"agentdam-privacy-leakage-evaluation-for","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","date":"2025-03-12","arxiv_id":"2503.09780","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":["facebookresearch/ai-agent-privacy"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"an-evaluation-of-llms-for-detecting-harmful","title":"An Evaluation of LLMs for Detecting Harmful Computing Terms","date":"2025-03-12","arxiv_id":"2503.09341","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-protect-yourself-from-5g-radiation","slug":"how-to-protect-yourself-from-5g-radiation","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","date":"2025-03-12","arxiv_id":"2503.09598","n_code_links":1,"syntology":null},{"paper":null,"slug":"un-straightening-generative-ai-how-queer","title":"Un-Straightening Generative AI: How Queer Artists Surface and Challenge the Normativity of Generative AI Models","date":"2025-03-12","arxiv_id":"2503.09805","n_code_links":0,"syntology":null},{"paper":null,"slug":"efpc-towards-efficient-and-flexible-prompt","title":"EFPC: Towards Efficient and Flexible Prompt Compression","date":"2025-03-11","arxiv_id":"2503.07956","n_code_links":0,"syntology":null},{"paper":"/paper/external-knowledge-injection-for-clip-based","slug":"external-knowledge-injection-for-clip-based","title":"External Knowledge Injection for CLIP-Based Class-Incremental Learning","date":"2025-03-11","arxiv_id":"2503.08510","n_code_links":3,"syntology":null},{"paper":null,"slug":"seeing-what-s-not-there-spurious-correlation","title":"Seeing What's Not There: Spurious Correlation in Multimodal LLMs","date":"2025-03-11","arxiv_id":"2503.08884","n_code_links":0,"syntology":null},{"paper":null,"slug":"bot-wars-evolved-orchestrating-competing-llms","title":"Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scams","date":"2025-03-10","arxiv_id":"2503.07036","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-multimodal-perception-in-large","title":"Exploring Multimodal Perception in Large Language Models Through Perceptual Strength Ratings","date":"2025-03-10","arxiv_id":"2503.06980","n_code_links":0,"syntology":null},{"paper":"/paper/large-model-enhanced-computational-ghost","slug":"large-model-enhanced-computational-ghost","title":"Large model enhanced computational ghost imaging","date":"2025-03-10","arxiv_id":"2503.08710","n_code_links":1,"syntology":null},{"paper":null,"slug":"skg-llm-developing-a-mathematical-model-for","title":"SKG-LLM: Developing a Mathematical Model for Stroke Knowledge Graph Construction Using Large Language Models","date":"2025-03-09","arxiv_id":"2503.06475","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-generative-ai-s-accuracy-and","title":"Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison","date":"2025-03-08","arxiv_id":"2503.16485","n_code_links":0,"syntology":null},{"paper":null,"slug":"db-explore-automated-database-exploration-and","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","date":"2025-03-06","arxiv_id":"2503.04959","n_code_links":0,"syntology":null},{"paper":null,"slug":"incentivizing-multi-tenant-split-federated","title":"Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge","date":"2025-03-06","arxiv_id":"2503.04971","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-to-address","slug":"leveraging-large-language-models-to-address","title":"Leveraging Large Language Models to Address Data Scarcity in Machine Learning: Applications in Graphene Synthesis","date":"2025-03-06","arxiv_id":"2503.04870","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-autonomous-reinforcement-learning-for","title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","date":"2025-03-06","arxiv_id":"2503.04280","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-finance-estimating","title":"Large language models in finance : what is financial sentiment?","date":"2025-03-05","arxiv_id":"2503.03612","n_code_links":0,"syntology":null},{"paper":"/paper/ma-lot-multi-agent-lean-based-long-chain-of","slug":"ma-lot-multi-agent-lean-based-long-chain-of","title":"MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving","date":"2025-03-05","arxiv_id":"2503.03205","n_code_links":1,"syntology":null},{"paper":null,"slug":"pretrained-llms-as-real-time-controllers-for","title":"Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line","date":"2025-03-05","arxiv_id":"2503.03889","n_code_links":0,"syntology":null},{"paper":null,"slug":"riskagent-autonomous-medical-ai-copilot-for","title":"RiskAgent: Autonomous Medical AI Copilot for Generalist Risk Prediction","date":"2025-03-05","arxiv_id":"2503.03802","n_code_links":0,"syntology":null},{"paper":null,"slug":"coserve-efficient-collaboration-of-experts","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","date":"2025-03-04","arxiv_id":"2503.02354","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-to-strong-generalization-even-in-random","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","date":"2025-03-04","arxiv_id":"2503.02877","n_code_links":0,"syntology":null},{"paper":null,"slug":"asktoact-enhancing-llms-tool-use-via-self","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","date":"2025-03-03","arxiv_id":"2503.01940","n_code_links":0,"syntology":null},{"paper":null,"slug":"unmasking-digital-falsehoods-a-comparative","title":"Unmasking Digital Falsehoods: A Comparative Analysis of LLM-Based Misinformation Detection Strategies","date":"2025-03-02","arxiv_id":"2503.00724","n_code_links":0,"syntology":null},{"paper":"/paper/2503-00455","slug":"2503-00455","title":"PodAgent: A Comprehensive Framework for Podcast Generation","date":"2025-03-01","arxiv_id":"2503.00455","n_code_links":1,"syntology":null},{"paper":null,"slug":"psychological-counseling-ability-of-large","title":"Psychological Counseling Ability of Large Language Models","date":"2025-03-01","arxiv_id":"2503.07627","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-align-multi-faceted-evaluation-a","title":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","date":"2025-02-26","arxiv_id":"2502.18874","n_code_links":0,"syntology":null},{"paper":null,"slug":"mebench-benchmarking-large-language-models","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","date":"2025-02-26","arxiv_id":"2502.18993","n_code_links":0,"syntology":null},{"paper":null,"slug":"reimagining-personal-data-unlocking-the","title":"Reimagining Personal Data: Unlocking the Potential of AI-Generated Images in Personal Data Meaning-Making","date":"2025-02-26","arxiv_id":"2502.18853","n_code_links":0,"syntology":null},{"paper":null,"slug":"weaker-llms-opinions-also-matter-mixture-of","title":"Weaker LLMs' Opinions Also Matter: Mixture of Opinions Enhances LLM's Mathematical Reasoning","date":"2025-02-26","arxiv_id":"2502.19622","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-in-agentic","title":"Assessing Large Language Models in Agentic Multilingual National Bias","date":"2025-02-25","arxiv_id":"2502.17945","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-optimization-for-controlled-image","title":"Bayesian Optimization for Controlled Image Editing via LLMs","date":"2025-02-25","arxiv_id":"2502.18116","n_code_links":0,"syntology":null},{"paper":null,"slug":"stackelberg-game-preference-optimization-for","title":"Stackelberg Game Preference Optimization for Data-Efficient Alignment of Language Models","date":"2025-02-25","arxiv_id":"2502.18099","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-data","title":"Are Large Language Models Good Data Preprocessors?","date":"2025-02-24","arxiv_id":"2502.16790","n_code_links":0,"syntology":null},{"paper":null,"slug":"logic-haystacks-probing-llms-long-context","title":"Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)","date":"2025-02-24","arxiv_id":"2502.17169","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llms-for-identifying-and","title":"Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation","date":"2025-02-22","arxiv_id":"2502.16022","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertainty-aware-fusion-an-ensemble","title":"Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models","date":"2025-02-22","arxiv_id":"2503.05757","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-bench-an-automated-benchmark-for","title":"Auto-Bench: An Automated Benchmark for Scientific Discovery in LLMs","date":"2025-02-21","arxiv_id":"2502.15224","n_code_links":0,"syntology":null},{"paper":null,"slug":"automedprompt-a-new-framework-for-optimizing","title":"AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradients","date":"2025-02-21","arxiv_id":"2502.15944","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-large-language-models","title":"Comparative Analysis of Large Language Models for Context-Aware Code Completion using SAFIM Framework","date":"2025-02-21","arxiv_id":"2502.15243","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-format-retrieval-augmented-generation","title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","date":"2025-02-21","arxiv_id":"2502.15604","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-pass-detection-of-jailbreaking-input","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","date":"2025-02-21","arxiv_id":"2502.15435","n_code_links":0,"syntology":null},{"paper":"/paper/turbofuzzllm-turbocharging-mutation-based","slug":"turbofuzzllm-turbocharging-mutation-based","title":"TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice","date":"2025-02-21","arxiv_id":"2502.18504","n_code_links":1,"syntology":null},{"paper":null,"slug":"argument-based-comparative-question-answering","title":"Argument-Based Comparative Question Answering Evaluation Benchmark","date":"2025-02-20","arxiv_id":"2502.14476","n_code_links":0,"syntology":null},{"paper":null,"slug":"deeprtl-bridging-verilog-understanding-and","title":"DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model","date":"2025-02-20","arxiv_id":"2502.15832","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-consider-security-an-empirical-study","title":"Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions","date":"2025-02-20","arxiv_id":"2502.14202","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-knowledge-generation-to-knowledge","title":"From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT","date":"2025-02-20","arxiv_id":"2502.14714","n_code_links":0,"syntology":null},{"paper":null,"slug":"full-step-dpo-self-supervised-preference","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","date":"2025-02-20","arxiv_id":"2502.14356","n_code_links":0,"syntology":null},{"paper":null,"slug":"kitab-bench-a-comprehensive-multi-domain","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","date":"2025-02-20","arxiv_id":"2502.14949","n_code_links":0,"syntology":null},{"paper":null,"slug":"paperhelper-knowledge-based-llm-qa-paper","title":"PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant","date":"2025-02-20","arxiv_id":"2502.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"tabular-embeddings-for-tables-with-bi","title":"Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting","date":"2025-02-20","arxiv_id":"2502.15819","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-social-connections-from-finnish","title":"Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs","date":"2025-02-19","arxiv_id":"2502.13566","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-correctness-to-comprehension-ai-agents","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","date":"2025-02-19","arxiv_id":"2502.13789","n_code_links":0,"syntology":null},{"paper":null,"slug":"star-sql-self-taught-reasoner-for-text-to-sql","title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","date":"2025-02-19","arxiv_id":"2502.13550","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-are-few-shot-graders","title":"Language Models are Few-Shot Graders","date":"2025-02-18","arxiv_id":"2502.13337","n_code_links":0,"syntology":null},{"paper":null,"slug":"matterchat-a-multi-modal-llm-for-material","title":"MatterChat: A Multi-Modal LLM for Material Science","date":"2025-02-18","arxiv_id":"2502.13107","n_code_links":0,"syntology":null},{"paper":"/paper/testing-prompt-engineering-methods-for","slug":"testing-prompt-engineering-methods-for","title":"Testing Prompt Engineering Methods for Knowledge Extraction from Text","date":"2025-02-18","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cmqcic-bench-a-chinese-benchmark-for","title":"CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation","date":"2025-02-17","arxiv_id":"2502.11703","n_code_links":0,"syntology":null},{"paper":"/paper/musc-improving-complex-instruction-following","slug":"musc-improving-complex-instruction-following","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","date":"2025-02-17","arxiv_id":"2502.11541","n_code_links":1,"syntology":null},{"paper":null,"slug":"smartllm-smart-contract-auditing-using-custom","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","date":"2025-02-17","arxiv_id":"2502.13167","n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-llms-in-predicting","title":"Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System","date":"2025-02-16","arxiv_id":"2502.10953","n_code_links":0,"syntology":null},{"paper":"/paper/exposing-numeracy-gaps-a-benchmark-to","slug":"exposing-numeracy-gaps-a-benchmark-to","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","date":"2025-02-16","arxiv_id":"2502.11075","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","n_code_links":0,"syntology":null},{"paper":null,"slug":"vendi-rag-adaptively-trading-off-diversity","title":"Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs","date":"2025-02-16","arxiv_id":"2502.11228","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-uniform-meaning-representation-help-gpt-4","title":"Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages?","date":"2025-02-13","arxiv_id":"2502.08900","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-tcm-question-answering-through-tree","title":"Improving TCM Question Answering through Tree-Organized Self-Reflective Retrieval with LLMs","date":"2025-02-13","arxiv_id":"2502.09156","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-evaluation-metrics-for-grammatical","slug":"rethinking-evaluation-metrics-for-grammatical","title":"Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?","date":"2025-02-13","arxiv_id":"2502.09416","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gotutiyan/gec-metrics"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fino1-on-the-transferability-of-reasoning","slug":"fino1-on-the-transferability-of-reasoning","title":"Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance","date":"2025-02-12","arxiv_id":"2502.08127","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["the-finai/fino1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/opengrok-enhancing-sns-data-processing-with","slug":"opengrok-enhancing-sns-data-processing-with","title":"OpenGrok: Enhancing SNS Data Processing with Distilled Knowledge and Mask-like Mechanisms","date":"2025-02-11","arxiv_id":"2502.07312","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-in-file","title":"Large Language Models for In-File Vulnerability Localization Can Be \"Lost in the End\"","date":"2025-02-09","arxiv_id":"2502.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"2502-05400","title":"Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data","date":"2025-02-08","arxiv_id":"2502.05400","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-understand-1","title":"Can Large Language Models Understand Intermediate Representations?","date":"2025-02-07","arxiv_id":"2502.06854","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-rising-threat-to-emerging-ai-powered","title":"Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search","date":"2025-02-07","arxiv_id":"2502.04951","n_code_links":0,"syntology":null},{"paper":"/paper/smi-an-information-theoretic-metric-for","slug":"smi-an-information-theoretic-metric-for","title":"SMI: An Information-Theoretic Metric for Predicting Model Knowledge Solely from Pre-Training Signals","date":"2025-02-06","arxiv_id":"2502.04066","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision-integrated-llms-for-autonomous-driving","title":"Vision-Integrated LLMs for Autonomous Driving Assistance : Human Performance Comparison and Trust Evaluation","date":"2025-02-06","arxiv_id":"2502.06843","n_code_links":0,"syntology":null},{"paper":null,"slug":"optic-optimizing-patient-provider-triaging","title":"OPTIC: Optimizing Patient-Provider Triaging & Improving Communications in Clinical Operations using GPT-4 Data Labeling and Model Distillation","date":"2025-02-05","arxiv_id":"2503.05701","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-panorama-of-anxiety-levels-a","title":"Exploring the Panorama of Anxiety Levels: A Multi-Scenario Study Based on Human-Centric Anxiety Level Detection and Personalized Guidance","date":"2025-02-04","arxiv_id":"2503.15527","n_code_links":0,"syntology":null},{"paper":"/paper/llmer-crafting-interactive-extended-reality","slug":"llmer-crafting-interactive-extended-reality","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","date":"2025-02-04","arxiv_id":"2502.02441","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-foundation-models-in-healthcare","title":"Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription","date":"2025-02-04","arxiv_id":"2502.04356","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-neurosymbolic-program-comprehension","title":"Toward Neurosymbolic Program Comprehension","date":"2025-02-03","arxiv_id":"2502.01806","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmark-on-peer-review-toxic-detection-a","title":"Benchmark on Peer Review Toxic Detection: A Challenging Task with a New Dataset","date":"2025-02-01","arxiv_id":"2502.01676","n_code_links":0,"syntology":null},{"paper":"/paper/do-llms-strategically-reveal-conceal-and","slug":"do-llms-strategically-reveal-conceal-and","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","date":"2025-01-31","arxiv_id":"2501.19398","n_code_links":1,"syntology":null},{"paper":null,"slug":"homogeneity-bias-as-differential-sampling","title":"Homogeneity Bias as Differential Sampling Uncertainty in Language Models","date":"2025-01-31","arxiv_id":"2501.19337","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-accuracy-in-emulating","title":"Large Language Models' Accuracy in Emulating Human Experts' Evaluation of Public Sentiments about Heated Tobacco Products on Social Media","date":"2025-01-31","arxiv_id":"2502.01658","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in-1","title":"Evaluating Large Language Models in Vulnerability Detection Under Variable Context Windows","date":"2025-01-30","arxiv_id":"2502.00064","n_code_links":0,"syntology":null},{"paper":null,"slug":"genie-generative-note-information-extraction","title":"GENIE: Generative Note Information Extraction model for structuring EHR data","date":"2025-01-30","arxiv_id":"2501.18435","n_code_links":0,"syntology":null},{"paper":null,"slug":"survey-and-improvement-strategies-for-gene","title":"Survey and Improvement Strategies for Gene Prioritization with Large Language Models","date":"2025-01-30","arxiv_id":"2501.18794","n_code_links":0,"syntology":null},{"paper":"/paper/unraveling-the-capabilities-of-language","slug":"unraveling-the-capabilities-of-language","title":"Unraveling the Capabilities of Language Models in News Summarization","date":"2025-01-30","arxiv_id":"2501.18128","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-graphs-for-table-and-text-based","title":"Hybrid Graphs for Table-and-Text based Question Answering using LLMs","date":"2025-01-29","arxiv_id":"2501.17767","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-in-context-learning-and-retrieval","title":"Leveraging In-Context Learning and Retrieval-Augmented Generation for Automatic Question Generation in Educational Domains","date":"2025-01-29","arxiv_id":"2501.17397","n_code_links":0,"syntology":null},{"paper":"/paper/jre-l-journalist-reader-and-editor-llms-in","slug":"jre-l-journalist-reader-and-editor-llms-in","title":"JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience","date":"2025-01-28","arxiv_id":"2501.16865","n_code_links":1,"syntology":null},{"paper":null,"slug":"scenario-understanding-of-traffic-scenes","title":"Scenario Understanding of Traffic Scenes Through Large Visual Language Models","date":"2025-01-28","arxiv_id":"2501.17131","n_code_links":0,"syntology":null},{"paper":"/paper/lctg-bench-llm-controlled-text-generation","slug":"lctg-bench-llm-controlled-text-generation","title":"LCTG Bench: LLM Controlled Text Generation Benchmark","date":"2025-01-27","arxiv_id":"2501.15875","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapting-biomedical-abstracts-into-plain","title":"Adapting Biomedical Abstracts into Plain language using Large Language Models","date":"2025-01-26","arxiv_id":"2501.15700","n_code_links":0,"syntology":null}],"record_sha256":"0ada62040d6da9f79c53aaec095838d174931f36f4e798af646f8363785190b6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}