RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, Tianyu Du
Abstract
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn’t previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model’s problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.- Anthology ID:
- 2024.findings-acl.281
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4730–4749
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-acl.281/
- DOI:
- 10.18653/v1/2024.findings-acl.281
- Cite (ACL):
- Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, and Tianyu Du. 2024. RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4730–4749, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (Liu et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-acl.281.pdf