| Title: |
AnchorCoT:Anchors Pave the Way for Multi-hop Reasoning |
| Authors: |
Ming, Tianshi; Wu, Xian; Zhang, Yingying; Fu, Zichuan; Cheng, Dawei |
| Contributors: |
Che, Wanxiang; Nabende, Joyce; Shutova, Ekaterina; Pilehvar, Mohammad Taher |
| Source: |
Ming, T, Wu, X, Zhang, Y, Fu, Z & Cheng, D 2025, AnchorCoT : Anchors Pave the Way for Multi-hop Reasoning. in W Che, J Nabende, E Shutova & M T Pilehvar (eds), ACL2025 - The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) - Findings of the Association for Computational Linguistics: ACL 2025. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Kerrville, TX, pp. 15522-15536, 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria, 27/07/25. https://doi.org/10.18653/v1/2025.findings-acl.801 |
| Publisher Information: |
Association for Computational Linguistics |
| Publication Year: |
2025 |
| Subject Terms: |
This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0 |
| Description: |
Large Language Models (LLMs) have made substantial strides in a broad array of natural language tasks. Recently, LLMs have demonstrated potential reasoning capabilities through prompt design, such as the Chain of Thought (CoT). Despite their superiority in question answering, LLMs still face challenges in answering questions that require multi-hop reasoning, often generating unreliable reasoning chains during answer generation. To improve LLMs' performance in multi-hop reasoning, we introduce a novel reasoning approach, AnchorCoT, designed to assist LLMs in answering questions involving complex logical reasoning steps. AnchorCoT first predicts key entities which work as important “anchors” to guide the reasoning process and then employs a novel ranking algorithm to ensure the logical sequence of the predicted answers. We implement AnchorCoT on Qwen2.5-7B/14B and GPT-4o and evaluate our method on widely used multi-hop reasoning datasets, including HotpotQA, 2WikiMulti-HopQA, and MuSiQue-Ans. The experimental results show that AnchorCoT outperforms existing methods in multi-hop question reasoning and provides more accurate reasoning results in multi-hop question answering tasks. © 2025 Association for Computational Linguistics. |
| Document Type: |
article in journal/newspaper |
| File Description: |
application/pdf |
| Language: |
English |
| ISBN: |
979-88-917-6256-5 |
| Relation: |
urn:ISBN:9798891762565 |
| DOI: |
10.18653/v1/2025.findings-acl.801 |
| Availability: |
https://scholars.cityu.edu.hk/en/publications/0df4fbc3-8ac1-4735-ba69-f91f84871aa7; https://scholars.cityu.edu.hk/ws/files/447605418/428654936.pdf; https://doi.org/10.18653/v1/2025.findings-acl.801; https://hdl.handle.net/2031/0df4fbc3-8ac1-4735-ba69-f91f84871aa7; http://www.scopus.com/inward/record.url?scp=105028636441&partnerID=8YFLogxK; https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105028636441&origin=recordpage |
| Rights: |
info:eu-repo/semantics/openAccess |
| Accession Number: |
edsbas.ED56F513 |
| Database: |
BASE |