{"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","slug":"gpt-4","name":"GPT-4","full_name":"GPT-4","full_name_withheld":false,"description_markdown":"**GPT-4** is a transformer based model pre-trained to predict the next token in a document.","description_state":"present","introduced_year":null,"introduced_by":{"title":"GPT-4 Technical Report","paper":"/paper/gpt-4-technical-report-1","first_author":"OpenAI","n_authors":282,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/gpt-4-technical-report-1"},"source":{"url":"https://arxiv.org/abs/2303.08774v5","title":"GPT-4 Technical Report","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":2870,"archive_num_papers":2871,"papers_newest_first":[{"paper":null,"slug":"foundation-models-for-logistics-toward","title":"Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces","date":"2025-07-15","arxiv_id":"2507.11352","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-evaluation-of-ai-powered-non","title":"An Empirical Evaluation of AI-Powered Non-Player Characters' Perceived Realism and Performance in Virtual Reality Environments","date":"2025-07-14","arxiv_id":"2507.10469","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-synthetic-labs-language-models","title":"Learning from Synthetic Labs: Language Models as Auction Participants","date":"2025-07-12","arxiv_id":"2507.09083","n_code_links":0,"syntology":null},{"paper":"/paper/agent-kb-leveraging-cross-domain-experience","slug":"agent-kb-leveraging-cross-domain-experience","title":"Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving","date":"2025-07-08","arxiv_id":"2507.06229","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":["oppo-personalai/agent-kb"],"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":"large-language-models-don-t-make-sense-of","title":"Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective","date":"2025-06-30","arxiv_id":"2506.24006","n_code_links":0,"syntology":null},{"paper":"/paper/probing-ai-safety-with-source-code","slug":"probing-ai-safety-with-source-code","title":"Probing AI Safety with Source Code","date":"2025-06-25","arxiv_id":"2506.20471","n_code_links":1,"syntology":null},{"paper":null,"slug":"lost-in-translation-converting-regexes-for","title":"Lost in Translation? Converting RegExes for Log Parsing into Dynatrace Pattern Language","date":"2025-06-24","arxiv_id":"2506.19539","n_code_links":0,"syntology":null},{"paper":null,"slug":"security-assessment-of-deepseek-and-gpt","title":"Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks","date":"2025-06-23","arxiv_id":"2506.18543","n_code_links":0,"syntology":null},{"paper":null,"slug":"swe-sql-illuminating-llm-pathways-to-solve","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","date":"2025-06-23","arxiv_id":"2506.18951","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-llms-to-assess-tutor-moves-in-real","title":"Leveraging LLMs to Assess Tutor Moves in Real-Life Dialogues: A Feasibility Study","date":"2025-06-20","arxiv_id":"2506.17410","n_code_links":0,"syntology":null},{"paper":"/paper/uprop-investigating-the-uncertainty","slug":"uprop-investigating-the-uncertainty","title":"UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making","date":"2025-06-20","arxiv_id":"2506.17419","n_code_links":1,"syntology":null},{"paper":"/paper/discosg-towards-discourse-level-text-scene","slug":"discosg-towards-discourse-level-text-scene","title":"DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement","date":"2025-06-18","arxiv_id":"2506.15583","n_code_links":2,"syntology":{"ran":17,"of":19,"n_ran_checked":9,"n_instrument":8,"unverified":2,"pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shaoqlin/discosg"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"i-know-which-llm-wrote-your-code-last-summer","title":"I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution","date":"2025-06-18","arxiv_id":"2506.17323","n_code_links":0,"syntology":null},{"paper":"/paper/impliret-benchmarking-the-implicit-fact","slug":"impliret-benchmarking-the-implicit-fact","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","date":"2025-06-17","arxiv_id":"2506.14407","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zeinabtaghavi/impliret"],"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":"scaling-intelligence-designing-data-centers","title":"Scaling Intelligence: Designing Data Centers for Next-Gen Language Models","date":"2025-06-17","arxiv_id":"2506.15006","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphabet-index-mapping-jailbreaking-llms","title":"Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity","date":"2025-06-15","arxiv_id":"2506.12685","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-cell-type-inference-in-vision","slug":"evaluating-cell-type-inference-in-vision","title":"Evaluating Cell Type Inference in Vision Language Models Under Varying Visual Context","date":"2025-06-15","arxiv_id":"2506.12683","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-models-enable-data-augmented","title":"Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials","date":"2025-06-14","arxiv_id":"2506.12557","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-helpful-context-for-llm-based","title":"Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study","date":"2025-06-13","arxiv_id":"2506.11561","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-gpt-4-for-vulnerability-witnessing","title":"Leveraging GPT-4 for Vulnerability-Witnessing Unit Test Generation","date":"2025-06-13","arxiv_id":"2506.11559","n_code_links":0,"syntology":null},{"paper":"/paper/2506-10297","slug":"2506-10297","title":"\"Check My Work?\": Measuring Sycophancy in a Simulated Educational Context","date":"2025-06-12","arxiv_id":"2506.10297","n_code_links":1,"syntology":null},{"paper":null,"slug":"2506-10527","title":"LogiPlan: A Structured Benchmark for Logical Planning and Relational Reasoning in LLMs","date":"2025-06-12","arxiv_id":"2506.10527","n_code_links":0,"syntology":null},{"paper":"/paper/swe-factory-your-automated-factory-for-issue","slug":"swe-factory-your-automated-factory-for-issue","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","date":"2025-06-12","arxiv_id":"2506.10954","n_code_links":1,"syntology":null},{"paper":"/paper/think-before-you-simulate-symbolic-reasoning-1","slug":"think-before-you-simulate-symbolic-reasoning-1","title":"Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering","date":"2025-06-12","arxiv_id":"2506.10753","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-llms-generate-good-stories-insights-and","title":"Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective","date":"2025-06-11","arxiv_id":"2506.10161","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-toxic-language","slug":"large-language-models-for-toxic-language","title":"Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages","date":"2025-06-11","arxiv_id":"2506.09992","n_code_links":1,"syntology":null},{"paper":null,"slug":"latent-multi-head-attention-for-small","title":"Latent Multi-Head Attention for Small Language Models","date":"2025-06-11","arxiv_id":"2506.09342","n_code_links":0,"syntology":null},{"paper":"/paper/mutual-supervised-learning-for-sequential-to","slug":"mutual-supervised-learning-for-sequential-to","title":"Mutual-Supervised Learning for Sequential-to-Parallel Code Translation","date":"2025-06-11","arxiv_id":"2506.11153","n_code_links":1,"syntology":null},{"paper":"/paper/counselbench-a-large-scale-expert-evaluation","slug":"counselbench-a-large-scale-expert-evaluation","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmark of Large Language Models in Mental Health Counseling","date":"2025-06-10","arxiv_id":"2506.08584","n_code_links":1,"syntology":null},{"paper":"/paper/tactic-translation-agents-with-cognitive","slug":"tactic-translation-agents-with-cognitive","title":"TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration","date":"2025-06-10","arxiv_id":"2506.08403","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-impact-of-fine-tuning-in-llama-on","title":"The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation","date":"2025-06-10","arxiv_id":"2506.08827","n_code_links":0,"syntology":null},{"paper":"/paper/can-ai-validate-science-benchmarking-llms-for","slug":"can-ai-validate-science-benchmarking-llms-for","title":"Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\\rightarrow$ Evidence Reasoning","date":"2025-06-09","arxiv_id":"2506.08235","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-bt-terms-back-translation-as-a-framework","title":"LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embedding","date":"2025-06-09","arxiv_id":"2506.08174","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-to-protection-a-comparative-study-of","title":"Prompt to Protection: A Comparative Study of Multimodal LLMs in Construction Hazard Recognition","date":"2025-06-09","arxiv_id":"2506.07436","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-tool-augmented-large-language-1","slug":"advancing-tool-augmented-large-language-1","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","date":"2025-06-05","arxiv_id":"2506.04625","n_code_links":1,"syntology":null},{"paper":null,"slug":"dynamic-context-tuning-for-retrieval","title":"Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation","date":"2025-06-05","arxiv_id":"2506.11092","n_code_links":0,"syntology":null},{"paper":null,"slug":"intentionally-unintentional-genai","title":"Intentionally Unintentional: GenAI Exceptionalism and the First Amendment","date":"2025-06-05","arxiv_id":"2506.05211","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-comprehensibility-of-multi-structured","slug":"on-the-comprehensibility-of-multi-structured","title":"On the Comprehensibility of Multi-structured Financial Documents using LLMs and Pre-processing Tools","date":"2025-06-05","arxiv_id":"2506.05182","n_code_links":1,"syntology":null},{"paper":null,"slug":"reasoning-or-overthinking-evaluating-large","title":"Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis","date":"2025-06-05","arxiv_id":"2506.04574","n_code_links":0,"syntology":null},{"paper":"/paper/failuresensoriq-a-multi-choice-qa-dataset-for","slug":"failuresensoriq-a-multi-choice-qa-dataset-for","title":"FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes","date":"2025-06-03","arxiv_id":"2506.03278","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-empirical-ai-research-outcomes","title":"Predicting Empirical AI Research Outcomes with Language Models","date":"2025-06-01","arxiv_id":"2506.00794","n_code_links":0,"syntology":null},{"paper":"/paper/sealqa-raising-the-bar-for-reasoning-in","slug":"sealqa-raising-the-bar-for-reasoning-in","title":"SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models","date":"2025-06-01","arxiv_id":"2506.01062","n_code_links":1,"syntology":null},{"paper":null,"slug":"machine-vs-machine-using-ai-to-tackle","title":"Machine vs Machine: Using AI to Tackle Generative AI Threats in Assessment","date":"2025-05-31","arxiv_id":"2506.02046","n_code_links":0,"syntology":null},{"paper":"/paper/translate-with-care-addressing-gender-bias","slug":"translate-with-care-addressing-gender-bias","title":"Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations","date":"2025-05-31","arxiv_id":"2506.00748","n_code_links":1,"syntology":null},{"paper":null,"slug":"persianmedqa-language-centric-evaluation-of","title":"PersianMedQA: Language-Centric Evaluation of LLMs in the Persian Medical Domain","date":"2025-05-30","arxiv_id":"2506.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"bounded-rationality-for-llms-satisficing","title":"Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time","date":"2025-05-29","arxiv_id":"2505.23729","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-based-code-generation-with","title":"Enhancing LLM-Based Code Generation with Complexity Metrics: A Feedback-Driven Approach","date":"2025-05-29","arxiv_id":"2505.23953","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-regulate-a-new-event-level","title":"Learning to Regulate: A New Event-Level Dataset of Capital Control Measures","date":"2025-05-29","arxiv_id":"2505.23025","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-association-biases-in-llm-moderation","title":"Probing Association Biases in LLM Moderation Over-Sensitivity","date":"2025-05-29","arxiv_id":"2505.23914","n_code_links":0,"syntology":null},{"paper":"/paper/table-r1-inference-time-scaling-for-table","slug":"table-r1-inference-time-scaling-for-table","title":"Table-R1: Inference-Time Scaling for Table Reasoning","date":"2025-05-29","arxiv_id":"2505.23621","n_code_links":1,"syntology":null},{"paper":"/paper/vf-eval-evaluating-multimodal-llms-for","slug":"vf-eval-evaluating-multimodal-llms-for","title":"VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos","date":"2025-05-29","arxiv_id":"2505.23693","n_code_links":1,"syntology":null},{"paper":null,"slug":"sosbench-benchmarking-safety-alignment-on","title":"SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge","date":"2025-05-27","arxiv_id":"2505.21605","n_code_links":0,"syntology":null},{"paper":"/paper/amqa-an-adversarial-dataset-for-benchmarking","slug":"amqa-an-adversarial-dataset-for-benchmarking","title":"AMQA: An Adversarial Dataset for Benchmarking Bias of LLMs in Medicine and Healthcare","date":"2025-05-26","arxiv_id":"2505.19562","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-specialization-benchmarking-llms-for","title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","date":"2025-05-26","arxiv_id":"2505.19851","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-reasoning-stalls-an","title":"Large Language Models' Reasoning Stalls: An Investigation into the Capabilities of Frontier Models","date":"2025-05-26","arxiv_id":"2505.19676","n_code_links":0,"syntology":null},{"paper":null,"slug":"lecode-a-benchmark-dataset-for-interactive","title":"LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation","date":"2025-05-26","arxiv_id":"2505.19667","n_code_links":0,"syntology":null},{"paper":"/paper/one-surrogate-to-fool-them-all-universal","slug":"one-surrogate-to-fool-them-all-universal","title":"One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP","date":"2025-05-26","arxiv_id":"2505.19840","n_code_links":1,"syntology":null},{"paper":"/paper/rearank-reasoning-re-ranking-agent-via","slug":"rearank-reasoning-re-ranking-agent-via","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","date":"2025-05-26","arxiv_id":"2505.20046","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":10,"n_instrument":2,"unverified":6,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["lezhang7/rearank"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-avengers-a-simple-recipe-for-uniting","slug":"the-avengers-a-simple-recipe-for-uniting","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","date":"2025-05-26","arxiv_id":"2505.19797","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-llm-based-agents-with-synthetic-self","title":"Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking","date":"2025-05-26","arxiv_id":"2505.20023","n_code_links":0,"syntology":null},{"paper":"/paper/vader-a-human-evaluated-benchmark-for","slug":"vader-a-human-evaluated-benchmark-for","title":"VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation","date":"2025-05-26","arxiv_id":"2505.19395","n_code_links":1,"syntology":null},{"paper":"/paper/assistant-guided-mitigation-of-teacher","slug":"assistant-guided-mitigation-of-teacher","title":"Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge","date":"2025-05-25","arxiv_id":"2505.19176","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-large-language-models-for-6","title":"Benchmarking Large Language Models for Cyberbullying Detection in Real-World YouTube Comments","date":"2025-05-25","arxiv_id":"2505.18927","n_code_links":0,"syntology":null},{"paper":null,"slug":"ghostprompt-jailbreaking-text-to-image","title":"GhostPrompt: Jailbreaking Text-to-image Generative Models based on Dynamic Optimization","date":"2025-05-25","arxiv_id":"2505.18979","n_code_links":0,"syntology":null},{"paper":null,"slug":"security-concerns-for-large-language-models-a","title":"Security Concerns for Large Language Models: A Survey","date":"2025-05-24","arxiv_id":"2505.18889","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-distillation-of-emotion-knowledge","slug":"contrastive-distillation-of-emotion-knowledge","title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition","date":"2025-05-23","arxiv_id":"2505.18040","n_code_links":1,"syntology":null},{"paper":"/paper/gaming-tool-preferences-in-agentic-llms","slug":"gaming-tool-preferences-in-agentic-llms","title":"Gaming Tool Preferences in Agentic LLMs","date":"2025-05-23","arxiv_id":"2505.18135","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-it-bad-to-work-all-the-time-cross-cultural","title":"Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4","date":"2025-05-23","arxiv_id":"2505.18322","n_code_links":0,"syntology":null},{"paper":"/paper/one-model-transfer-to-all-on-robust-jailbreak","slug":"one-model-transfer-to-all-on-robust-jailbreak","title":"One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs","date":"2025-05-23","arxiv_id":"2505.17598","n_code_links":1,"syntology":null},{"paper":null,"slug":"explain-less-understand-more-jargon-detection","title":"Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16227","n_code_links":0,"syntology":null},{"paper":null,"slug":"bountybench-dollar-impact-of-ai-agent","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","date":"2025-05-21","arxiv_id":"2505.15216","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-command","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","date":"2025-05-21","arxiv_id":"2505.15088","n_code_links":0,"syntology":null},{"paper":"/paper/cad-coder-an-open-source-vision-language","slug":"cad-coder-an-open-source-vision-language","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","date":"2025-05-20","arxiv_id":"2505.14646","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["anniedoris/cad-coder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cost-augmented-monte-carlo-tree-search-for","title":"Cost-Augmented Monte Carlo Tree Search for LLM-Assisted Planning","date":"2025-05-20","arxiv_id":"2505.14656","n_code_links":0,"syntology":null},{"paper":null,"slug":"dsmentor-enhancing-data-science-agents-with","title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","date":"2025-05-20","arxiv_id":"2505.14163","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-testing-in-llms-insights-into","title":"Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities","date":"2025-05-19","arxiv_id":"2505.13195","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-good-at-detecting","title":"Are Large Language Models Good at Detecting Propaganda?","date":"2025-05-19","arxiv_id":"2505.13706","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-rag-methods-for","title":"Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain","date":"2025-05-19","arxiv_id":"2505.13006","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-hidden-structure-improving-legal-document","title":"The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting","date":"2025-05-19","arxiv_id":"2505.12837","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaloop-assessing-llm-robustness-in","title":"EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective","date":"2025-05-18","arxiv_id":"2505.12185","n_code_links":0,"syntology":null},{"paper":"/paper/verireason-reinforcement-learning-with-1","slug":"verireason-reinforcement-learning-with-1","title":"VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation","date":"2025-05-17","arxiv_id":"2505.11849","n_code_links":1,"syntology":null},{"paper":null,"slug":"2505-10862","title":"Have Multimodal Large Language Models (MLLMs) Really Learned to Tell the Time on Analog Clocks?","date":"2025-05-16","arxiv_id":"2505.10862","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-10936","title":"Connecting the Dots: A Chain-of-Collaboration Prompting Framework for LLM Agents","date":"2025-05-16","arxiv_id":"2505.10936","n_code_links":0,"syntology":null},{"paper":null,"slug":"vaiage-a-multi-agent-solution-to-personalized","title":"Vaiage: A Multi-Agent Solution to Personalized Travel Planning","date":"2025-05-16","arxiv_id":"2505.10922","n_code_links":0,"syntology":null},{"paper":null,"slug":"2505-10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","date":"2025-05-15","arxiv_id":"2505.10717","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-collective-reasoning-in-multi-agent","title":"Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks","date":"2025-05-15","arxiv_id":"2505.11556","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-security-audit-using-large","title":"Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment","date":"2025-05-15","arxiv_id":"2505.10732","n_code_links":0,"syntology":null},{"paper":"/paper/comparing-llm-text-annotation-skills-a-study","slug":"comparing-llm-text-annotation-skills-a-study","title":"Comparing LLM Text Annotation Skills: A Study on Human Rights Violations in Social Media Data","date":"2025-05-15","arxiv_id":"2505.10260","n_code_links":1,"syntology":null},{"paper":"/paper/on-technique-identification-and-threat-actor","slug":"on-technique-identification-and-threat-actor","title":"On Technique Identification and Threat-Actor Attribution using LLMs and Embedding Models","date":"2025-05-15","arxiv_id":"2505.11547","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-act-multi-step-planning-and-reasoning","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","date":"2025-05-15","arxiv_id":"2505.09970","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-prompt-optimizers-from-prompt","slug":"rethinking-prompt-optimizers-from-prompt","title":"Rethinking Prompt Optimizers: From Prompt Merits to Optimization","date":"2025-05-15","arxiv_id":"2505.09930","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-analysis-of-large-language","title":"A Comprehensive Analysis of Large Language Model Outputs: Similarity, Diversity, and Bias","date":"2025-05-14","arxiv_id":"2505.09056","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-hungry-is-ai-benchmarking-energy-water","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","date":"2025-05-14","arxiv_id":"2505.09598","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-suite-of-lms-comprehend-puzzle-statements","title":"A suite of LMs comprehend puzzle statements as well as humans","date":"2025-05-13","arxiv_id":"2505.08996","n_code_links":0,"syntology":null},{"paper":"/paper/ac-reason-towards-theory-guided-actual","slug":"ac-reason-towards-theory-guided-actual","title":"AC-Reason: Towards Theory-Guided Actual Causality Reasoning with Large Language Models","date":"2025-05-13","arxiv_id":"2505.08750","n_code_links":1,"syntology":null},{"paper":null,"slug":"for-gpt-4-as-with-humans-information","title":"For GPT-4 as with Humans: Information Structure Predicts Acceptability of Long-Distance Dependencies","date":"2025-05-13","arxiv_id":"2505.09005","n_code_links":0,"syntology":null},{"paper":"/paper/healthbench-evaluating-large-language-models","slug":"healthbench-evaluating-large-language-models","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","date":"2025-05-13","arxiv_id":"2505.08775","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/simple-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/judging-the-judges-can-large-vision-language","slug":"judging-the-judges-can-large-vision-language","title":"Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?","date":"2025-05-13","arxiv_id":"2505.08468","n_code_links":1,"syntology":null},{"paper":"/paper/lost-in-transmission-when-and-why-llms-fail","slug":"lost-in-transmission-when-and-why-llms-fail","title":"Lost in Transmission: When and Why LLMs Fail to Reason Globally","date":"2025-05-13","arxiv_id":"2505.08140","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/openthinkimg-learning-to-think-with-images","slug":"openthinkimg-learning-to-think-with-images","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08617","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_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":387,"every_run_a_failure_of_syntologys_instrument":139,"listed_with_a_run_with_no_instrument_failure":387,"listed_every_run_a_failure_of_syntologys_instrument":139,"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"},"papers_where_code_ran":526,"papers_where_code_ran_first_page":"/method/gpt-4/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":29,"url":"/method/gpt-4/papers/2","json":"/method/gpt-4/papers/2.json","rows":100},{"order":"archive","page":3,"of":29,"url":"/method/gpt-4/papers/3","json":"/method/gpt-4/papers/3.json","rows":100},{"order":"archive","page":4,"of":29,"url":"/method/gpt-4/papers/4","json":"/method/gpt-4/papers/4.json","rows":100},{"order":"archive","page":5,"of":29,"url":"/method/gpt-4/papers/5","json":"/method/gpt-4/papers/5.json","rows":100},{"order":"archive","page":6,"of":29,"url":"/method/gpt-4/papers/6","json":"/method/gpt-4/papers/6.json","rows":100},{"order":"archive","page":7,"of":29,"url":"/method/gpt-4/papers/7","json":"/method/gpt-4/papers/7.json","rows":100},{"order":"archive","page":8,"of":29,"url":"/method/gpt-4/papers/8","json":"/method/gpt-4/papers/8.json","rows":100},{"order":"archive","page":9,"of":29,"url":"/method/gpt-4/papers/9","json":"/method/gpt-4/papers/9.json","rows":100},{"order":"archive","page":10,"of":29,"url":"/method/gpt-4/papers/10","json":"/method/gpt-4/papers/10.json","rows":100},{"order":"archive","page":11,"of":29,"url":"/method/gpt-4/papers/11","json":"/method/gpt-4/papers/11.json","rows":100},{"order":"archive","page":12,"of":29,"url":"/method/gpt-4/papers/12","json":"/method/gpt-4/papers/12.json","rows":100},{"order":"archive","page":13,"of":29,"url":"/method/gpt-4/papers/13","json":"/method/gpt-4/papers/13.json","rows":100},{"order":"archive","page":14,"of":29,"url":"/method/gpt-4/papers/14","json":"/method/gpt-4/papers/14.json","rows":100},{"order":"archive","page":15,"of":29,"url":"/method/gpt-4/papers/15","json":"/method/gpt-4/papers/15.json","rows":100},{"order":"archive","page":16,"of":29,"url":"/method/gpt-4/papers/16","json":"/method/gpt-4/papers/16.json","rows":100},{"order":"archive","page":17,"of":29,"url":"/method/gpt-4/papers/17","json":"/method/gpt-4/papers/17.json","rows":100},{"order":"archive","page":18,"of":29,"url":"/method/gpt-4/papers/18","json":"/method/gpt-4/papers/18.json","rows":100},{"order":"archive","page":19,"of":29,"url":"/method/gpt-4/papers/19","json":"/method/gpt-4/papers/19.json","rows":100},{"order":"archive","page":20,"of":29,"url":"/method/gpt-4/papers/20","json":"/method/gpt-4/papers/20.json","rows":100},{"order":"archive","page":21,"of":29,"url":"/method/gpt-4/papers/21","json":"/method/gpt-4/papers/21.json","rows":100},{"order":"archive","page":22,"of":29,"url":"/method/gpt-4/papers/22","json":"/method/gpt-4/papers/22.json","rows":100},{"order":"archive","page":23,"of":29,"url":"/method/gpt-4/papers/23","json":"/method/gpt-4/papers/23.json","rows":100},{"order":"archive","page":24,"of":29,"url":"/method/gpt-4/papers/24","json":"/method/gpt-4/papers/24.json","rows":100},{"order":"archive","page":25,"of":29,"url":"/method/gpt-4/papers/25","json":"/method/gpt-4/papers/25.json","rows":100},{"order":"archive","page":26,"of":29,"url":"/method/gpt-4/papers/26","json":"/method/gpt-4/papers/26.json","rows":100},{"order":"archive","page":27,"of":29,"url":"/method/gpt-4/papers/27","json":"/method/gpt-4/papers/27.json","rows":100},{"order":"archive","page":28,"of":29,"url":"/method/gpt-4/papers/28","json":"/method/gpt-4/papers/28.json","rows":100},{"order":"archive","page":29,"of":29,"url":"/method/gpt-4/papers/29","json":"/method/gpt-4/papers/29.json","rows":70},{"order":"ran","page":1,"of":6,"url":"/method/gpt-4/papers/ran/1","json":"/method/gpt-4/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":6,"url":"/method/gpt-4/papers/ran/2","json":"/method/gpt-4/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":6,"url":"/method/gpt-4/papers/ran/3","json":"/method/gpt-4/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":6,"url":"/method/gpt-4/papers/ran/4","json":"/method/gpt-4/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":6,"url":"/method/gpt-4/papers/ran/5","json":"/method/gpt-4/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":6,"url":"/method/gpt-4/papers/ran/6","json":"/method/gpt-4/papers/ran/6.json","rows":26}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":447},{"task":"/task/language-modeling","name":"Language Modeling","papers":322},{"task":"/task/large-language-model","name":"Large Language Model","papers":298},{"task":"/task/question-answering","name":"Question Answering","papers":251},{"task":"/task/retrieval","name":"Retrieval","papers":167},{"task":"/task/decision-making","name":"Decision Making","papers":122},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":121},{"task":"/task/benchmarking","name":"Benchmarking","papers":120},{"task":"/task/rag","name":"RAG","papers":111},{"task":"/task/code-generation","name":"Code Generation","papers":110},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":109},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":105},{"task":"/task/text-generation","name":"Text Generation","papers":99},{"task":"/task/math","name":"Math","papers":94},{"task":"/task/hallucination","name":"Hallucination","papers":87},{"task":"/task/multiple-choice","name":"Multiple-choice","papers":79},{"task":"/task/sentence","name":"Sentence","papers":69},{"task":"/task/instruction-following","name":"Instruction Following","papers":68},{"task":"/task/mathematical-reasoning","name":"Mathematical Reasoning","papers":58},{"task":"/task/chatbot","name":"Chatbot","papers":57}],"tasks_shown":20,"n_tasks":734,"usage_by_year":[{"year":"2023","papers":883},{"year":"2024","papers":1637},{"year":"2025","papers":350}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gpt-4"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=GPT-4","read_at":"2026-10-05T00:57:10+00:00","query":"GPT-4","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2303.08774","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":false,"bearers_found":1,"served":null,"leading_other_bearer":{"arxiv_id":"2305.03195","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","citations":91,"named_by":["title_prefix"],"bearer_name":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","ask_with":"have('2305.03195')"},"n_other_bearers_listed":1,"note":"Nothing resolved to 'GPT-4' by name, but 1 thing(s) here DECLARE that name -- most cited: the paper 'Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing' (arXiv:2305.03195, 91 citations). None of them is a well-cited bearer of the name, so this is still a coverage gap for any better-known sense -- they are listed so you can judge, not as a substitute."},"name_competition_text":"Nothing resolved to this name, but 1 entry in Syntology's graph carry it; the most cited is the paper “Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing” (arXiv:2305.03195, 91 citations). None of them is well cited, so for any better known sense of the name this is still a gap in coverage; they are listed so you can judge, not as a substitute.","near_matches":["GPT","GPT-D","H-GPT","RF-GPT","MS-GPT","GPT-RE","VA-GPT","GPT-ST"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"ad0abd99f8fd53b468f4b0600f4ae653fbaa40fdb130a82bdd2d354ebf9f1fc3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}