公平性能否被提示？基于提示的去偏策略在高风险推荐系统中的应用

摘要

大型語言模型（LLMs）能透過姓名、代名詞等間接線索推斷性別或年齡等敏感屬性，可能導致推薦結果產生偏差。儘管現有多種去偏方法，但它們需調用模型權重、計算成本高昂，且普通用戶無法直接使用。為解決這一問題，我們探究了LLM推薦系統（LLMRecs）中的隱性偏差，並探索基於提示的策略能否作為輕量易用的去偏途徑。我們提出了三種針對LLMRecs的偏差感知提示策略。據我們所知，這是首個聚焦用戶群體公平性的LLMRecs提示去偏研究。通過在3個LLM、4種提示模板、9類敏感屬性值及2個數據集上的實驗表明，我們提出的「要求LLM保持公平」的去偏方法可將公平性提升最高達74%，同時保持相當的推薦效能，但在某些情況下可能過度推廣特定人口統計群體。

English

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.

公平性能否被提示？基于提示的去偏策略在高风险推荐系统中的应用

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

摘要

Support