FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
원문 초록
Training large language models (LLMs) is a costly endeavour in terms of time and computational resources. The large amount of training data used during the unsupervised pre-training phase makes it difficult to verify all data and, unfortunately, undesirable data may be ingested during training. Re-training from scratch is impractical and has led to the creation of the 'unlearning' discipline where models are modified to "unlearn" undesirable information without retraining. However, any modification can alter the behaviour of LLMs, especially on key dimensions such as fairness. This is the first work that examines this interplay between unlearning and fairness for LLMs. In particular, we focus on a popular unlearning framework known as SISA [Bourtoule et al., 2021], which creates an ensemble of models trained on disjoint shards. We evaluate the performance-fairness trade-off for SISA, and empirically demsontrate that SISA can indeed reduce fairness in LLMs. To remedy this, we propose post-processing bias mitigation techniques for ensemble models produced by SISA. We adapt the post-processing fairness improvement technique from [Hardt et al., 2016] to design three methods that can handle model ensembles, and prove that one of the methods is an optimal fair predictor for ensemble of models. Through experimental results, we demonstrate the efficacy of our post-processing framework called 'FairSISA'.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
Guiding LLM Decision-Making with Fairness Reward Models
Fairness Is Not Enough: Auditing Competence and Intersectional Bias in AI-powered Resume Screening
Datasets for Fairness in Language Models: An In-Depth Survey
hyperFA*IR: A hypergeometric approach to fair rankings with finite candidate pool
토론
이 논문과 연결된 포럼 글이 아직 없습니다.