{"work":{"id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","openalex_id":null,"doi":"10.1007/s10664-008-","arxiv_id":"2303.17651","raw_key":null,"title":"Self-Refine: Iterative Refinement with Self-Feedback","authors":null,"authors_text":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe","year":2023,"venue":"cs.CL","abstract":"Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and feedback provider. We evaluate Self-Refine across 7 diverse tasks, ranging from dialog response generation to mathematical reasoning, using state-of-the-art (GPT-3.5, ChatGPT, and GPT-4) LLMs. Across all evaluated tasks, outputs generated with Self-Refine are preferred by humans and automatic metrics over those generated with the same LLM using conventional one-step generation, improving by ~20% absolute on average in task performance. Our work demonstrates that even state-of-the-art LLMs like GPT-4 can be further improved at test time using our simple, standalone approach.","external_url":"https://arxiv.org/abs/2303.17651","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T21:57:37.951501+00:00","pith_arxiv_id":"2303.17651","created_at":"2026-05-09T05:55:31.895576+00:00","updated_at":"2026-07-11T11:50:26.030339+00:00","title_quality_ok":true,"display_title":"Self-Refine: Iterative Refinement with Self-Feedback","render_title":"Self-Refine: Iterative Refinement with Self-Feedback"},"hub":{"state":{"work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":148,"external_cited_by_count":null,"distinct_field_count":13,"first_pith_cited_at":"2023-03-20T18:08:50+00:00","last_pith_cited_at":"2026-07-08T18:43:34+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T08:29:28.082688+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":23},{"context_role":"baseline","n":2},{"context_role":"method","n":2},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":19},{"context_polarity":"unclear","n":3},{"context_polarity":"baseline","n":2},{"context_polarity":"use_method","n":2},{"context_polarity":"support","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Self-Refine: Iterative Refinement with Self-Feedback","claims":[{"claim_text":"Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and f","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"InProceedings of 41st IEEE/ACM International Conference on Automated Software Engineering (ASE '26).ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/nnnnnnn.nnnnnnn 1 Introduction Software engineering agents powered by large language models are increasingly deployed in complex real-world settings, including repository-level code repair [2, 37, 41], enterprise workflow automa- tion [23], and cloud service operations [1, 9, 10, 17]. As these agents tackle broader and more complex tasks, f","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"(6624):1092-1097, 2022. 5, 9 [16] H. Liu, L. Lee, K. Lee, and P. Abbeel. Instruction-following agents with jointly pre-trained vision-language models. arXiv preprint arXiv:2210.13431, 2022. 9 [17] N. Liu, S. Li, Y . Du, A. Torralba, and J. B. Tenenbaum. Compositional visual generation with composable diffusion models. arXiv preprint arXiv:2206.01714, 2022. 9 [18] A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y . Yang, et al. Self-refine: Ite","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"∆ and cross-model Kendall τ as concrete robustness metrics, and propose an evaluation card schema for disclosing the protocol stack behind each reported pass@k. 2 Related Work General code debugging and program repair.LLM-based code debugging is well studied in general-purpose programming. DebugBench [33] evaluates repair on buggy C++, Java, and Python 2 programs; SWE-bench [11] asks models to resolve real GitHub issues; Self-Debugging [16] studies iterative repair with execution feedback; and C","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Large language model (LLM) agents are increasingly used to solve tasks that require multi-step interaction rather than single-shot prediction. In software engineering, web navigation, tool use, data analysis, and interactive decision-making, agents must plan over multiple steps, call external tools, inspect intermediate states, and revise their behavior based on feedback [11, 16, 22, 28]. A recurring observation across these settings is that successful agent trajectories often contain reusable p","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"YuhaoLi,YulinHu,YunanHuang,YunjiLi,YunzhiXu,YuxinMao,YuxuanShi,YuzeWenren,ZehanLi, Zelin Li, Zhanxu Tian, Zhengmao Zhu, Zhenhua Fan, Zhenzhen Wu, Zhichao Xu, Zhihang Yu, Zhiheng Lyu, Zhuo Jiang, Zibo Gao, Zijia Wu, Zijian Song, and Zijun Sun. Minimax-m1: Scaling test-time compute efficiently with lightning attention, 2025. URLhttps://arxiv.org/abs/2506.13585. 3, 9, 19 [36] Krista Opsahl-Ong, Michael J Ryan, Josh Purtell, David Broman, Christopher Potts, Matei Zaharia, and Omar Khattab. Optimizin","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Automated retrieval Generative Agents [22], Memory- bank [170], AgentSims [174], etc. Interactive retrieval Memory Sandbox[176], ChatDB [175], etc. Reasoning & Planning §3.1.4 Reasoning CoT [95], Zero-shot-CoT [96], Self-Consistency [97], Self- Polish [99], Selection-Inference [177], Self-Refine [178], etc. Planing Plan formulation Least-to-Most [98], SayCan [179], Hug- gingGPT [180], ToT [181], PET [182], DEPS [183], RAP [184], SwiftSage [185], LLM+P [125], MRKL [186], etc. Plan reflection LLM-","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Self-Refine: Iterative Refinement with Self-Feedback because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (22 contexts).","role_counts":[{"n":22,"context_role":"background"},{"n":2,"context_role":"baseline"},{"n":2,"context_role":"method"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-23T22:44:46.156111+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"1f8c3531-2599-4fc5-93b8-c74fc813e36e","orcid":null,"display_name":"Aman Madaan"},{"id":"28fe90d4-a98a-48ec-b504-e4b7b65e8cf5","orcid":null,"display_name":"Niket Tandon"},{"id":"9bd4669b-e9ea-4bd7-9dac-d01ee5ae78ea","orcid":null,"display_name":"Prakhar Gupta"},{"id":"2c872943-fb0e-4698-b48c-97806ab06a06","orcid":null,"display_name":"Skyler Hallinan"},{"id":"3b991f39-08a6-4938-bd28-cd3fd97144c4","orcid":null,"display_name":"Luyu Gao"},{"id":"65c73d4e-6beb-47a9-a064-fb1d1c2a7ec4","orcid":null,"display_name":"Sarah Wiegreffe"}]},"error":null,"updated_at":"2026-05-23T22:44:46.915844+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T10:28:55.658016+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":25},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":19},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":15},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":13},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":12},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":12},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":12},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":10},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":9},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":8},{"title":"Large Language Models Cannot Self-Correct Reasoning Yet","work_id":"f63b261b-ef16-40f5-993b-9d37b1a51b92","shared_citers":8},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":8},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":8},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":7},{"title":"Le, Denny Zhou, and Xinyun Chen","work_id":"cacd55e1-79db-4dd6-9f1b-794fc09d75bb","shared_citers":7},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":7},{"title":"ARXIV.ORG , year =","work_id":"80a320e6-5d7a-4c12-bc44-46f43550db56","shared_citers":6},{"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","shared_citers":6},{"title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","work_id":"dcdfa0ce-7ed4-4614-acd9-8bdbf491fc26","shared_citers":6},{"title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","work_id":"f20ed1da-2676-4598-a11b-54549718735b","shared_citers":6}],"time_series":[{"n":6,"year":2023},{"n":5,"year":2024},{"n":1,"year":2025},{"n":47,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T10:28:47.140604+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":"2026-05-14T10:28:49.427579+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Self-Refine: Iterative Refinement with Self-Feedback","claims":[{"claim_text":"Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and f","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"InProceedings of 41st IEEE/ACM International Conference on Automated Software Engineering (ASE '26).ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/nnnnnnn.nnnnnnn 1 Introduction Software engineering agents powered by large language models are increasingly deployed in complex real-world settings, including repository-level code repair [2, 37, 41], enterprise workflow automa- tion [23], and cloud service operations [1, 9, 10, 17]. As these agents tackle broader and more complex tasks, f","claim_type":"dataset","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"(6624):1092-1097, 2022. 5, 9 [16] H. Liu, L. Lee, K. Lee, and P. Abbeel. Instruction-following agents with jointly pre-trained vision-language models. arXiv preprint arXiv:2210.13431, 2022. 9 [17] N. Liu, S. Li, Y . Du, A. Torralba, and J. B. Tenenbaum. Compositional visual generation with composable diffusion models. arXiv preprint arXiv:2206.01714, 2022. 9 [18] A. Madaan, N. Tandon, P. Gupta, S. Hallinan, L. Gao, S. Wiegreffe, U. Alon, N. Dziri, S. Prabhumoye, Y . Yang, et al. Self-refine: Ite","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"∆ and cross-model Kendall τ as concrete robustness metrics, and propose an evaluation card schema for disclosing the protocol stack behind each reported pass@k. 2 Related Work General code debugging and program repair.LLM-based code debugging is well studied in general-purpose programming. DebugBench [33] evaluates repair on buggy C++, Java, and Python 2 programs; SWE-bench [11] asks models to resolve real GitHub issues; Self-Debugging [16] studies iterative repair with execution feedback; and C","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Large language model (LLM) agents are increasingly used to solve tasks that require multi-step interaction rather than single-shot prediction. In software engineering, web navigation, tool use, data analysis, and interactive decision-making, agents must plan over multiple steps, call external tools, inspect intermediate states, and revise their behavior based on feedback [11, 16, 22, 28]. A recurring observation across these settings is that successful agent trajectories often contain reusable p","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"YuhaoLi,YulinHu,YunanHuang,YunjiLi,YunzhiXu,YuxinMao,YuxuanShi,YuzeWenren,ZehanLi, Zelin Li, Zhanxu Tian, Zhengmao Zhu, Zhenhua Fan, Zhenzhen Wu, Zhichao Xu, Zhihang Yu, Zhiheng Lyu, Zhuo Jiang, Zibo Gao, Zijia Wu, Zijian Song, and Zijun Sun. Minimax-m1: Scaling test-time compute efficiently with lightning attention, 2025. URLhttps://arxiv.org/abs/2506.13585. 3, 9, 19 [36] Krista Opsahl-Ong, Michael J Ryan, Josh Purtell, David Broman, Christopher Potts, Matei Zaharia, and Omar Khattab. Optimizin","claim_type":"method","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Automated retrieval Generative Agents [22], Memory- bank [170], AgentSims [174], etc. Interactive retrieval Memory Sandbox[176], ChatDB [175], etc. Reasoning & Planning §3.1.4 Reasoning CoT [95], Zero-shot-CoT [96], Self-Consistency [97], Self- Polish [99], Selection-Inference [177], Self-Refine [178], etc. Planing Plan formulation Least-to-Most [98], SayCan [179], Hug- gingGPT [180], ToT [181], PET [182], DEPS [183], RAP [184], SwiftSage [185], LLM+P [125], MRKL [186], etc. Plan reflection LLM-","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Self-Refine: Iterative Refinement with Self-Feedback because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (22 contexts).","role_counts":[{"n":22,"context_role":"background"},{"n":2,"context_role":"baseline"},{"n":2,"context_role":"method"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-23T22:44:46.928958+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Self-Refine: Iterative Refinement with Self-Feedback","claims":[{"claim_text":"Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and f","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Self-Refine: Iterative Refinement with Self-Feedback because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T10:28:51.369939+00:00"}},"summary":{"title":"Self-Refine: Iterative Refinement with Self-Feedback","claims":[{"claim_text":"Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement. The main idea is to generate an initial output using an LLMs; then, the same LLMs provides feedback for its output and uses it to refine itself, iteratively. Self-Refine does not require any supervised training data, additional training, or reinforcement learning, and instead uses a single LLM as the generator, refiner, and f","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Self-Refine: Iterative Refinement with Self-Feedback because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":25},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":19},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":15},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":13},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":12},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":12},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":12},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":10},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":9},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":8},{"title":"Large Language Models Cannot Self-Correct Reasoning Yet","work_id":"f63b261b-ef16-40f5-993b-9d37b1a51b92","shared_citers":8},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":8},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":8},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":7},{"title":"Le, Denny Zhou, and Xinyun Chen","work_id":"cacd55e1-79db-4dd6-9f1b-794fc09d75bb","shared_citers":7},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":7},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":7},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":7},{"title":"ARXIV.ORG , year =","work_id":"80a320e6-5d7a-4c12-bc44-46f43550db56","shared_citers":6},{"title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","shared_citers":6},{"title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","work_id":"dcdfa0ce-7ed4-4614-acd9-8bdbf491fc26","shared_citers":6},{"title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","work_id":"f20ed1da-2676-4598-a11b-54549718735b","shared_citers":6}],"time_series":[{"n":6,"year":2023},{"n":5,"year":2024},{"n":1,"year":2025},{"n":47,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"1f8c3531-2599-4fc5-93b8-c74fc813e36e","orcid":null,"display_name":"Aman Madaan","source":"manual","import_confidence":0.72},{"id":"3b991f39-08a6-4938-bd28-cd3fd97144c4","orcid":null,"display_name":"Luyu Gao","source":"manual","import_confidence":0.72},{"id":"28fe90d4-a98a-48ec-b504-e4b7b65e8cf5","orcid":null,"display_name":"Niket Tandon","source":"manual","import_confidence":0.72},{"id":"9bd4669b-e9ea-4bd7-9dac-d01ee5ae78ea","orcid":null,"display_name":"Prakhar Gupta","source":"manual","import_confidence":0.72},{"id":"65c73d4e-6beb-47a9-a064-fb1d1c2a7ec4","orcid":null,"display_name":"Sarah Wiegreffe","source":"manual","import_confidence":0.72},{"id":"2c872943-fb0e-4698-b48c-97806ab06a06","orcid":null,"display_name":"Skyler Hallinan","source":"manual","import_confidence":0.72}]}}