ICR: Iterative Clarification and Rewriting for Conversational Search
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915495872036864 |
|---|---|
| author | Cao, Zhiyu Li, Peifeng Zhu, Qiaoming |
| author_facet | Cao, Zhiyu Li, Peifeng Zhu, Qiaoming |
| contents | Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05100 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ICR: Iterative Clarification and Rewriting for Conversational Search Cao, Zhiyu Li, Peifeng Zhu, Qiaoming Computation and Language Artificial Intelligence Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets. |
| title | ICR: Iterative Clarification and Rewriting for Conversational Search |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.05100 |