Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
Top Cited Papers
Open Access
- 14 September 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 993-999
Abstract
The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm — Recommendation via LLM (RecLLM). Nevertheless, it is important to note that LLMs may contain social prejudices, and therefore, the fairness of recommendations made by RecLLM requires further investigation. To avoid the potential risks of RecLLM, it is imperative to evaluate the fairness of RecLLM with respect to various sensitive attributes on the user side. Due to the differences between the RecLLM paradigm and the traditional recommendation paradigm, it is problematic to directly use the fairness benchmark of traditional recommendation. To address the dilemma, we propose a novel benchmark called Fairness of Recommendation via LLM (FaiRLLM). This benchmark comprises carefully crafted metrics and a dataset that accounts for eight sensitive attributes1 in two recommendation scenarios: music and movies. By utilizing our FaiRLLM benchmark, we conducted an evaluation of ChatGPT and discovered that it still exhibits unfairness to some sensitive attributes when generating recommendations. Our code and dataset can be found at https://github.com/jizhi-zhang/FaiRLLM.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Practical Compositional Fairness: Understanding Fairness in Multi-Component Recommender Systems2021
- On the negative impact of social influence in recommender systems: A study of bribery in collaborative hybrid algorithmsInformation Processing & Management, 2020
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models2020
- CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models2020
- Social Biases in NLP Models as Barriers for Persons with Disabilities2020
- Fairness in Recommendation Ranking through Pairwise Comparisons2019
- Controlling Popularity Bias in Learning-to-Rank Recommendation2017
- HCI for Recommender Systems2016
- Exploring the filter bubble2014
- Social recommendation: a reviewSocial Network Analysis and Mining, 2013