Abstract
Attributing answer text to its source document for information-seeking questions is crucial for building trustworthy, reliable, and accountable systems. We formulate a new task of post-hoc answer attribution for long document comprehension (LDC). Owing to the lack of long-form abstractive and information-seeking LDC datasets, we refactor existing datasets to assess the strengths and weaknesses of existing retrieval-based and proposed answer decomposition and textual entailment-based optimal selection attribution systems for this task. We throw light on the limitations of existing datasets and the need for datasets to assess the actual performance of systems on this task.- Anthology ID:
- 2024.starsem-1.4
- Volume:
- Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Danushka Bollegala, Vered Shwartz
- Venue:
- *SEM
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 49–57
- Language:
- URL:
- https://aclanthology.org/2024.starsem-1.4
- DOI:
- Cite (ACL):
- Abhilasha Sancheti, Koustava Goswami, and Balaji Srinivasan. 2024. Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 49–57, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges (Sancheti et al., *SEM 2024)
- PDF:
- https://preview.aclanthology.org/jeptaln-2024-ingestion/2024.starsem-1.4.pdf