Abstract
This paper studies the problem of information retrieval, to adapt to unseen tasks. Existing work generates synthetic queries from domain-specific documents to jointly train the retriever. However, the conventional query generator assumes the query as a question, thus failing to accommodate general search intents. A more lenient approach incorporates task-adaptive elements, such as few-shot learning with an 137B LLM. In this paper, we challenge a trend equating query and question, and instead conceptualize query generation task as a “compilation” of high-level intent into task-adaptive query. Specifically, we propose EGG, a query generator that better adapts to wide search intents expressed in the BeIR benchmark. Our method outperforms baselines and existing models on four tasks with underexplored intents, while utilizing a query generator 47 times smaller than the previous state-of-the-art. Our findings reveal that instructing the LM with explicit search intent is a key aspect of modeling an effective query generator.- Anthology ID:
- 2024.findings-emnlp.274
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4775–4785
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.274
- DOI:
- 10.18653/v1/2024.findings-emnlp.274
- Cite (ACL):
- Yoonsang Lee, Minsoo Kim, and Seung-won Hwang. 2024. Disentangling Questions from Query Generation for Task-Adaptive Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 4775–4785, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Disentangling Questions from Query Generation for Task-Adaptive Retrieval (Lee et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.274.pdf