{"work":{"id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","openalex_id":null,"doi":null,"arxiv_id":"2305.14325","raw_key":null,"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","authors":null,"authors_text":"Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, Igor Mordatch","year":2023,"venue":"cs.CL","abstract":"Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. We also demonstrate that our approach improves the factual validity of generated content, reducing fallacious answers and hallucinations that contemporary models are prone to. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we investigate. Overall, our findings suggest that such \"society of minds\" approach has the potential to significantly advance the capabilities of LLMs and pave the way for further breakthroughs in language generation and understanding.","external_url":"https://arxiv.org/abs/2305.14325","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-24T00:53:40.696700+00:00","pith_arxiv_id":"2305.14325","created_at":"2026-05-10T00:59:49.378308+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","render_title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate"},"hub":{"state":{"work_id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":78,"external_cited_by_count":null,"distinct_field_count":15,"first_pith_cited_at":"2023-05-30T15:25:45+00:00","last_pith_cited_at":"2026-05-19T17:54:21+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-12T07:59:21.540676+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":20},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":19},{"context_polarity":"baseline","n":1},{"context_polarity":"support","n":1},{"context_polarity":"use_method","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:49:32.813445+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":12},{"title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","work_id":"920bbf2b-e5b9-4d6e-a597-b82621d19ef9","shared_citers":11},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":7},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":7},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":6},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":6},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":6},{"title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","work_id":"eac74d79-d8d1-49dd-8565-53d713a84fff","shared_citers":5},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":5},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":5},{"title":"Large Language Models Cannot Self-Correct Reasoning Yet","work_id":"f63b261b-ef16-40f5-993b-9d37b1a51b92","shared_citers":5},{"title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","work_id":"dcdfa0ce-7ed4-4614-acd9-8bdbf491fc26","shared_citers":4},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":4},{"title":"Let's Verify Step by Step","work_id":"6d05b790-04c5-4fd2-91b2-ba1dfdd5770f","shared_citers":4},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":4},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":4},{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","work_id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","shared_citers":4},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":4},{"title":"AI safety via debate","work_id":"13c1ec37-af93-438a-bdf0-f2eafaee5635","shared_citers":3},{"title":"arXiv:2509.05396 [cs]","work_id":"56e70929-251f-4dfe-b21b-83787255f30d","shared_citers":3},{"title":"arXiv preprint arXiv:2308.10848 , year=","work_id":"3187ed22-d803-437a-88c1-abab6eeb2af6","shared_citers":3},{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","work_id":"ba431bb8-7f34-4a9e-9b03-51585294d7d3","shared_citers":3}],"time_series":[{"n":5,"year":2023},{"n":1,"year":2024},{"n":2,"year":2025},{"n":32,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T17:49:55.277755+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T17:49:58.652124+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","claims":[{"claim_text":"Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Improving Factuality and Reasoning in Language Models through Multiagent Debate because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T17:49:38.779882+00:00"}},"summary":{"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","claims":[{"claim_text":"Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Improving Factuality and Reasoning in Language Models through Multiagent Debate because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":12},{"title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","work_id":"920bbf2b-e5b9-4d6e-a597-b82621d19ef9","shared_citers":11},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":7},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":7},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":6},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":6},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":6},{"title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","work_id":"eac74d79-d8d1-49dd-8565-53d713a84fff","shared_citers":5},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":5},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":5},{"title":"Large Language Models Cannot Self-Correct Reasoning Yet","work_id":"f63b261b-ef16-40f5-993b-9d37b1a51b92","shared_citers":5},{"title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","work_id":"dcdfa0ce-7ed4-4614-acd9-8bdbf491fc26","shared_citers":4},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":4},{"title":"Let's Verify Step by Step","work_id":"6d05b790-04c5-4fd2-91b2-ba1dfdd5770f","shared_citers":4},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":4},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":4},{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","work_id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","shared_citers":4},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":4},{"title":"AI safety via debate","work_id":"13c1ec37-af93-438a-bdf0-f2eafaee5635","shared_citers":3},{"title":"arXiv:2509.05396 [cs]","work_id":"56e70929-251f-4dfe-b21b-83787255f30d","shared_citers":3},{"title":"arXiv preprint arXiv:2308.10848 , year=","work_id":"3187ed22-d803-437a-88c1-abab6eeb2af6","shared_citers":3},{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","work_id":"ba431bb8-7f34-4a9e-9b03-51585294d7d3","shared_citers":3}],"time_series":[{"n":5,"year":2023},{"n":1,"year":2024},{"n":2,"year":2025},{"n":32,"year":2026}],"dependency_candidates":[]},"authors":[]}}