Learning to break: Knowledge-enhanced reasoning in multi-agent debate system
Authors:
- Haotian WangHWHaotian Wang
- Xiyuan DuXDXiyuan Du
- Weijiang YuWYWeijiang Yu
- Qianglong ChenQCQianglong Chen
- Kun ZhuKZKun Zhu
- Zheng ChuZCZheng Chu
- Lian YanLYLian Yan
- Yi GuanYGYi Guan
- 3 December 2024
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 618
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2021ZD0113302, 2021ZD0110900)
This publication has 17 references indexed in Scilit:
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- In-Context Retrieval-Augmented Language ModelsTransactions of the Association for Computational Linguistics, 2023
- Information retrieval algorithms and neural ranking models to detect previously fact-checked informationNeurocomputing, 2023
- WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences2023
- Active Retrieval Augmented Generation2023
- Do Large Language Models Know What They Don’t Know?2023
- An autonomous debating systemNature, 2021
- Retrieval Augmentation Reduces Hallucination in Conversation2021
- Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps2020
- Dense Passage Retrieval for Open-Domain Question Answering2020