Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929371442315264 |
|---|---|
| author | Chen, Haonan Dou, Zhicheng Mao, Kelong Liu, Jiongnan Zhao, Ziliang |
| author_facet | Chen, Haonan Dou, Zhicheng Mao, Kelong Liu, Jiongnan Zhao, Ziliang |
| contents | 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). ConvAug first generates multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07092 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation Chen, Haonan Dou, Zhicheng Mao, Kelong Liu, Jiongnan Zhao, Ziliang Computation and Language Information Retrieval 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). ConvAug first generates multi-level augmented conversations to capture the diverse nature of conversational contexts. Inspired by human cognition, we devise a cognition-aware 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. |
| title | Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2402.07092 |