Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise
Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, Joyce Whang
Abstract
Most existing retrieval-augmented language models (LMs) assume a naive dichotomy within a retrieved document set: query-relevance and irrelevance. Our work investigates a more challenging scenario in which even the “relevant” documents may contain misleading or incorrect information, causing conflict among the retrieved documents and thereby negatively influencing model decisions as noise. We observe that existing LMs are highly brittle to the presence of conflicting information in both the fine-tuning and in-context few-shot learning scenarios. We propose approaches for handling knowledge conflicts among retrieved documents by explicitly fine-tuning a discriminator or prompting GPT-3.5 to elicit its discriminative capability. Our empirical results on open-domain QA show that these approaches significantly enhance model robustness. We also provide our findings on incorporating the fine-tuned discriminator’s decision into the in-context learning process, proposing a way to exploit the benefits of two disparate learning schemes. Alongside our findings, we provide MacNoise, a machine-generated, conflict-induced dataset to further encourage research in this direction.- Anthology ID:
- 2024.findings-naacl.159
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2024
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2474–2495
- Language:
- URL:
- https://aclanthology.org/2024.findings-naacl.159
- DOI:
- Cite (ACL):
- Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, and Joyce Whang. 2024. Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2474–2495, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise (Hong et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2024.findings-naacl.159.pdf