{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:38:26Z","timestamp":1770932306792,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of the Hong Kong SAR","award":["11217823"],"award-info":[{"award-number":["11217823"]}]},{"name":"Collaborative Research Fund","award":["C1042-23GF"],"award-info":[{"award-number":["C1042-23GF"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371411"],"award-info":[{"award-number":["62371411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK initiative"},{"name":"Government of the HKSAR"},{"name":"Laboratory for AI-Powered Financial Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3581101","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:28:10Z","timestamp":1750426090000},"page":"1318-1328","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Correctness-Based Learning for Efficient Reasoning via Automated Process Supervision"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3955-7272","authenticated-orcid":false,"given":"Yuxuan","family":"Yao","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"given":"Mingyang","family":"Liu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9557-5308","authenticated-orcid":false,"given":"Guanzhi","family":"Deng","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3825-5474","authenticated-orcid":false,"given":"Zengyan","family":"Liu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1755-0183","authenticated-orcid":false,"given":"Dapeng","family":"Wu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6232-5957","authenticated-orcid":false,"given":"Zhijiang","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8008-064X","authenticated-orcid":false,"given":"Han","family":"Wu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2756-4984","authenticated-orcid":false,"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref2","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. 9th Int. Conf. Learn. Representations, ICLR 2021, Virtual Event","author":"Hendrycks","year":"2021"},{"key":"ref5","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref6","article-title":"AutoGen: Enabling next-gen LLM applications via multi-agent conversation framework","author":"Wu","year":"2024","journal-title":"Proc. 1st Conf. Lang. Modeling"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref8","article-title":"A survey of hallucination in large foundation models","author":"Rawte","year":"2023"},{"key":"ref9","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022"},{"key":"ref10","article-title":"SELF-GUIDE: Better task-specific instruction following via self-synthetic finetuning","author":"Zhao","year":"2024"},{"key":"ref11","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst. 2022","author":"Ouyang","year":"2022"},{"key":"ref12","article-title":"Instruction tuning with GPT-4","author":"Peng","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00660"},{"key":"ref14","first-page":"1051","article-title":"Large language models can self-improve","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Huang","year":"2023"},{"key":"ref15","article-title":"CRITIC: Large language models can self-correct with tool-interactive critiquing","author":"Gou","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00626"},{"key":"ref17","article-title":"Tora: A tool-integrated reasoning agent for mathematical problem solving","author":"Gou","year":"2023"},{"key":"ref18","article-title":"Learning from mistakes makes LLM better reasoner","author":"An","year":"2023"},{"key":"ref19","article-title":"Large language models cannot self-correct reasoning yet","author":"Huang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2891895"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.011"},{"key":"ref22","article-title":"Lets verify step by step","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Lightman","year":"2024"},{"key":"ref23","article-title":"Solving math word problems with process- and outcome-based feedback","author":"Uesato","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.296"},{"key":"ref25","article-title":"Lets verify step by step","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Lightman","year":"2023"},{"key":"ref26","article-title":"DQ-LoRe: Dual queries with low rank approximation re-ranking for in-context learning","author":"Xiong","year":"2023"},{"key":"ref27","first-page":"84482","article-title":"SOAP: Enhancing efficiency of generated code via self-optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2024"},{"key":"ref28","article-title":"Process-driven autoformalization in lean 4","author":"Lu","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.910"},{"key":"ref30","article-title":"Improving language models via plug-and-play retrieval feedback","author":"Yu","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.82"},{"key":"ref32","article-title":"Generating sequences by learning to self-correct","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Welleck","year":"2023"},{"key":"ref33","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Madaan","year":"2023"},{"key":"ref34","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36: Annu. Conf. Neural Inf. Process. Syst. 2023","author":"Shinn","year":"2023"},{"key":"ref35","first-page":"41618","article-title":"Self-evaluation guided beam search for reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36: Annu. Conf. Neural Inf. Process. Syst. 2023","author":"Xie","year":"2023"},{"key":"ref36","article-title":"LLM self defense: By self examination, LLMS know they are being tricked","author":"Helbling","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.177"},{"key":"ref38","article-title":"AUTOCV: Empowering reasoning with automated process labeling via confidence variation","author":"Lu","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.679"},{"key":"ref40","article-title":"Learning from correctness without prompting makes LLM efficient reasoner","author":"Yao","year":"2024","journal-title":"Proc. 1st Conf. Lang. Modeling"},{"key":"ref41","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf Process. Syst. 2022","author":"Wei","year":"2022"},{"key":"ref42","article-title":"Complexity-based prompting for multi-step reasoning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Fu","year":"2023"},{"key":"ref43","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao","year":"2023"},{"key":"ref44","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref45","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst. 2022","author":"Kojima","year":"2022"},{"key":"ref46","article-title":"Large language models as analogical reasoners","author":"Yasunaga","year":"2023"},{"key":"ref47","first-page":"30378","article-title":"The unreliability of explanations in few-shot prompting for textual reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst. 2022","author":"Ye","year":"2022"},{"key":"ref48","article-title":"Large language models are human-level prompt engineers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhou","year":"2023"},{"issue":"70","key":"ref49","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","article-title":"Orca: Progressive learning from complex explanation traces of GPT-4","author":"Mukherjee","year":"2023"},{"key":"ref51","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023"},{"key":"ref52","article-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","author":"Luo","year":"2023"},{"key":"ref53","article-title":"Tuning language models by proxy","author":"Liu","year":"2024"},{"key":"ref54","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"7309","DOI":"10.18653\/v1\/2024.findings-emnlp.429","article-title":"Multi-step problem solving through a verifier: An empirical analysis on model-induced process supervision","volume-title":"Proc. Findings Assoc. Comput. Linguistics: EMNLP 2024","author":"Wang","year":"2024"},{"key":"ref57","article-title":"Improve mathematical reasoning in language models by automated process supervision","author":"Luo","year":"2024"},{"key":"ref58","article-title":"Generating with confidence: Uncertainty quantification for black-box large language models","author":"Lin","year":"2023"},{"key":"ref59","article-title":"Confidence matters: Revisiting intrinsic self-correction capabilities of large language models","author":"Li","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref62","article-title":"Measuring mathematical problem solving with the MATH dataset","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks 1, NeurIPS Datasets Benchmarks 2021 virtual","author":"Hendrycks"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1015"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11332"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00370"},{"key":"ref67","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024"},{"key":"ref68","first-page":"12375","article-title":"Lets sample step by step: Adaptive-consistency for efficient reasoning and coding with LLMS","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Aggarwal","year":"2023"},{"key":"ref69","first-page":"39648","article-title":"Language models can solve computer tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36: Annu. Conf. Neural Inf. Process. Syst. 2023","author":"Kim","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"ref71","article-title":"Qwen2 technical report","volume-title":"Proc. 13th Int. Joint Conf. Natural Lang. Process. Asia-Pacific Chapter Assoc. Comput. Linguistics","author":"Yang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11045818.pdf?arnumber=11045818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:48Z","timestamp":1770929988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":72,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3581101","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}