Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations

TL;DR

This paper explores prompt-based strategies to mitigate biases in large language model recommenders, aiming for a lightweight, user-friendly approach to improve fairness without extensive retraining.

Contribution

It introduces three novel prompt-based debiasing strategies for LLM recommenders, focusing on group fairness and demonstrating their effectiveness across multiple models and datasets.

Findings

Fairness improved by up to 74% using prompt strategies

Approach maintains recommendation effectiveness

Potential overpromotion of certain demographic groups

Abstract

Large Language Models (LLMs) can infer sensitive attributes such as gender or age from indirect cues like names and pronouns, potentially biasing recommendations. While several debiasing methods exist, they require access to the LLMs' weights, are computationally costly, and cannot be used by lay users. To address this gap, we investigate implicit biases in LLM Recommenders (LLMRecs) and explore whether prompt-based strategies can serve as a lightweight and easy-to-use debiasing approach. We contribute three bias-aware prompting strategies for LLMRecs. To our knowledge, this is the first study on prompt-based debiasing approaches in LLMRecs that focuses on group fairness for users. Our experiments with 3 LLMs, 4 prompt templates, 9 sensitive attribute values, and 2 datasets show that our proposed debiasing approach, which instructs an LLM to be fair, can improve fairness by up to 74% while retaining comparable effectiveness, but might overpromote specific demographic groups in some cases.