Changtai Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Changtai Zhu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Xipeng Qiu
Fudan University, China
3 shared publications Linyang Li
School of Computer Science Key Laboratory of Intelligent Information Processing Fudan University Shanghai Fudan University
2 shared publicationsTianxiang Sun
School of Computer Science Key Laboratory of Intelligent Information Processing Fudan University Shanghai Fudan University
2 shared publicationsXiaonan Li
School of Computer Science Key Laboratory of Intelligent Information Processing Fudan University Shanghai Fudan University
2 shared publicationsZhangyue Yin
School of Computer Science Key Laboratory of Intelligent Information Processing Fudan University Shanghai Fudan University
2 shared publications- Kai Song
Bytedance Inc
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26558-26575
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 26558-26575
Open AccessConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
LLatrieval: LLM-Verified Retrieval for Verifiable Generation
Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM's output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferior to LLMs since they often have much fewer parameters than the large language model and have not been demonstrated to scale well to the size of LLMs. If the retriever does not correctly find the supporting documents, the LLM can not generate the correct and verifiable answer, which overshadows the LLM's remarkable abilities. To address these limitations, we propose \LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Thus, the LLM can iteratively provide feedback to retrieval and facilitate the retrieval result to fully support verifiable generation. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
Open AccessLLatrieval: LLM-Verified Retrieval for Verifiable Generation
Verifiable generation aims to let the large language model (LLM) generate text with supporting documents, which enables the user to flexibly verify the answer and makes the LLM's output more reliable. Retrieval plays a crucial role in verifiable generation. Specifically, the retrieved documents not only supplement knowledge to help the LLM generate correct answers, but also serve as supporting evidence for the user to verify the LLM's output. However, the widely used retrievers become the bottleneck of the entire pipeline and limit the overall performance. Their capabilities are usually inferior to LLMs since they often have much fewer parameters than the large language model and have not been demonstrated to scale well to the size of LLMs. If the retriever does not correctly find the supporting documents, the LLM can not generate the correct and verifiable answer, which overshadows the LLM's remarkable abilities. To address these limitations, we propose \LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Thus, the LLM can iteratively provide feedback to retrieval and facilitate the retrieval result to fully support verifiable generation. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5453-5471
LLatrieval: LLM-Verified Retrieval for Verifiable Generation
Xiaonan Li, Changtai Zhu, Linyang Li, Zhangyue Yin, Tianxiang Sun, Xipeng Qiu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5453-5471
Open AccessLLatrieval: LLM-Verified Retrieval for Verifiable Generation
Xiaonan Li, Changtai Zhu, Linyang Li, Zhangyue Yin, Tianxiang Sun, Xipeng Qiu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.