Zero-Shot Retrieval with Search Agents and Hybrid EnvironmentsDownload PDF

Published: 01 Feb 2023, Last Modified: 14 Jul 2024Submitted to ICLR 2023Readers: Everyone
Keywords: learning to search, information retrieval, document ranking, relevance feedback, zero shot, language models, behavioral cloning
TL;DR: A learning to search agent combined with a hybrid dense-sparse retrieval environment achieves sota on zero shot retrieval (BEIR).
Abstract: Learning to search is the task of building artificial agents that learn to autonomously use a search box to find information. So far, it has been shown that current language models can learn symbolic query reformulation policies, in combination with traditional term-based retrieval, but fall short of outperforming neural retrievers. We extend the previous learning to search setup to a hybrid environment, which accepts discrete query refinement operations, after a first-pass retrieval step performed by a dual encoder. Experiments on the BEIR task show that search agents, trained via behavioral cloning, outperform the underlying search system based on a combined dual encoder retriever and cross encoder reranker. Furthermore, we find that simple heuristic Hybrid Retrieval Environments (HRE) can improve baseline performance by several nDCG points. The search agent based on the HRE environment (HaRE) produces state-of-the-art performance on both zero-shot and in-domain evaluations. We carry out an extensive qualitative analysis to shed light on the agents policies.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](https://www.catalyzex.com/paper/zero-shot-retrieval-with-search-agents-and/code)
4 Replies

Loading