Daiqing Qi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Daiqing Qi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Sheng Li
University of Virginia, Charlottesville, Virginia, USA
2 shared publications - Aidong Zhang
Department of Computer Science, University of Virginia, Charlottesville, USA
1 shared publication - Dongliang Guo
University of Virginia University of Virginia University of Virginia The University of Texas at Dallas University of Virginia University of Virginia
1 shared publication - Handong Zhao
Adobe Research
1 shared publication Hongyi Wu
1 shared publication- Mengxuan Hu
School of Data Science, University of Virginia, Charlottesville, VA, United States
1 shared publication
Latest Publications
- 7 December 2024
- Published by Springer Nature
- p. 285-300
Generalizing to Unseen Domains via Text-Guided Augmentation: A Training-Free Approach
- 7 December 2024
- Published by Springer Nature
- p. 285-300
Generalizing to Unseen Domains via Text-Guided Augmentation: A Training-Free Approach
- Open Access
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs.
Open AccessNo Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs.