CoTMind: A closed-loop framework for optimizing Chain-of-Thought reasoning in complex question answering
Authors:
- Guoquan LuGLGuoquan Lu
- Weixiao ZhanWZWeixiao Zhan
- Lin PengLPLin Peng
- Li LiLLLi Li
- 21 July 2026
- journal article
- Published by Elsevier in Information Processing & Management
- Vol. 64 (1)
Abstract
No abstract availableThis publication has 7 references indexed in Scilit:
- MedScaleRE-PF: a prompt-based framework with retrieval-augmented generation, chain-of-thought, and self-verification for scale-specific relation extraction in Chinese medical literatureInformation Processing & Management, 2025
- Enhancing scientific table understanding with type-guided chain-of-thoughtInformation Processing & Management, 2025
- Source-Free Domain Adaptation for Question Answering with Masked Self-trainingTransactions of the Association for Computational Linguistics, 2024
- From chatting to self-educating: Can AI tools boost student learning outcomes?Expert Systems with Applications, 2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- Did Aristotle Use a Laptop?A Question Answering Benchmark with Implicit Reasoning StrategiesTransactions of the Association for Computational Linguistics, 2021
- SPARQA: Skeleton-Based Semantic Parsing for Complex Questions over Knowledge BasesProceedings of the AAAI Conference on Artificial Intelligence, 2020