{"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,"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,"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,"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","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,"unverified":0,"pointer_only":0}},{"paper":null,"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","title":"Probing AI Safety with Source Code","date":"2025-06-25","arxiv_id":"2506.20471","n_code_links":1,"syntology":null},{"paper":null,"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,"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,"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,"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","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","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":1,"of":19,"unverified":18,"pointer_only":19}},{"paper":null,"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","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","date":"2025-06-17","arxiv_id":"2506.14407","n_code_links":1,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":2}},{"paper":null,"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,"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","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,"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,"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,"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","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,"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","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","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,"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","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,"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","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","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","title":"TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration","date":"2025-06-10","arxiv_id":"2506.08403","n_code_links":1,"syntology":null}],"papers_shown":30,"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":"2026-09-24T18:15:14+00:00"}