Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision

Philipp Christmann, Svitlana Vakulenko, Ionut Teodor Sorodoc, Bill Byrne, Adrià de Gispert


Abstract
Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset.
Anthology ID:
2024.findings-emnlp.835
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:
14301–14310
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.835
DOI:
10.18653/v1/2024.findings-emnlp.835
Bibkey:
Cite (ACL):
Philipp Christmann, Svitlana Vakulenko, Ionut Teodor Sorodoc, Bill Byrne, and Adrià de Gispert. 2024. Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14301–14310, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision (Christmann et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.835.pdf