Reimagining Retrieval Augmented Language Models for Answering Queries
Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Wen-tau Yih
Abstract
We present a reality check on large language models and inspect the promise of retrieval-augmented language models in comparison. Such language models are semi-parametric, where models integrate model parameters and knowledge from external data sources to make their predictions, as opposed to the parametric nature of vanilla large language models. We give initial experimental findings that semi-parametric architectures can be enhanced with views, a query analyzer/planner, and provenance to make a significantly more powerful system for question answering in terms of accuracy and efficiency, and potentially for other NLP tasks.- Anthology ID:
- 2023.findings-acl.382
- Original:
- 2023.findings-acl.382v1
- Version 2:
- 2023.findings-acl.382v2
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6131–6146
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.382
- DOI:
- 10.18653/v1/2023.findings-acl.382
- Cite (ACL):
- Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, and Wen-tau Yih. 2023. Reimagining Retrieval Augmented Language Models for Answering Queries. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6131–6146, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Reimagining Retrieval Augmented Language Models for Answering Queries (Tan et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-acl.382.pdf