AGR: Age Group fairness Reward for Bias Mitigation in LLMs
This addresses age bias in LLMs, a relatively unexplored area compared to racial and gender biases, though it is incremental as it adapts existing RLHF methods to a new domain.
The paper tackled age bias in LLMs by constructing age bias datasets and introducing an age fairness reward, which significantly improved response accuracy and reduced performance disparities across age groups.
LLMs can exhibit age biases, resulting in unequal treatment of individuals across age groups. While much research has addressed racial and gender biases, age bias remains little explored. The scarcity of instruction-tuning and preference datasets for age bias hampers its detection and measurement, and existing fine-tuning methods seldom address age-related fairness. In this paper, we construct age bias preference datasets and instruction-tuning datasets for RLHF. We introduce ARG, an age fairness reward to reduce differences in the response quality of LLMs across different age groups. Extensive experiments demonstrate that this reward significantly improves response accuracy and reduces performance disparities across age groups. Our source code and datasets are available at the anonymous \href{https://anonymous.4open.science/r/FairRLHF-D445/readme.md}{link}.