Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation

Haonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu, Ziliang Zhao


Abstract
Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem – that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug). We first generate multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware prompting process to mitigate the generation of false positives, false negatives, and hallucinations. Moreover, we develop a difficulty-adaptive sample filter that selects challenging samples for complex conversations, thereby giving the model a larger learning space. A contrastive learning objective is then employed to train a better conversational context encoder. Extensive experiments conducted on four public datasets, under both normal and zero-shot settings, demonstrate the effectiveness, generalizability, and applicability of ConvAug. The code is released at https://github.com/haon-chen/ConvAug.
Anthology ID:
2024.acl-long.149
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2700–2718
Language:
URL:
https://aclanthology.org/2024.acl-long.149
DOI:
Bibkey:
Cite (ACL):
Haonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu, and Ziliang Zhao. 2024. Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2700–2718, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation (Chen et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.149.pdf