Whose Opinions Do Language Models Reflect?

By Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, Tatsunori B. Hashimoto. 2023

917 citations recorded by the source corpus.

Language models (LMs) are increasingly being used in open-ended contexts, where the opinions reflected by LMs in response to subjective queries can have a profound impact, both on user satisfaction, as well as shaping the views of society at large. In this work, we put forth a quantitative framework to investigate the opinions reflected by LMs -- by leveraging high-quality public opinion polls and their associated human responses. Using this framework, we create OpinionsQA, a new dataset for evaluating the alignment of LM opinions with those of 60 US demographic groups over topics ranging from abortion to automation. Across topics, we find substantial misalignment between the views reflected by current LMs and those of US demographic groups: on par with the Democrat-Republican divide on climate change. Notably, this misalignment persists even after explicitly steering the LMs towards particular demographic groups. Our analysis not only confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs, but also surfaces groups whose opinions are poorly reflected by current LMs (e.g., 65+ and widowed individuals). Our code and data are available at https://github.com/tatsu-lab/opinions_qa.

Subfields: Artificial Intelligence, General Social Sciences, Large Language Models, Evaluation & Benchmarks, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Percy Liang
  3. Luke S. Zettlemoyer
  4. Jianfeng Gao
  5. Yejin Choi
  6. Sergey Levine
  7. Kyunghyun Cho
  8. Yoshua Bengio

In General Social Sciences

  1. Matei A. Zaharia
  2. James Y. Zou
  3. Anton Bakhtin
  4. Diyi Yang
  5. Anca Dragan
  6. Esin Durmus
  7. Jiaao Chen

In Large Language Models

  1. Omar Shaikh
  2. Matei A. Zaharia
  3. Peter Hase
  4. James Y. Zou
  5. Anton Bakhtin
  6. Mario Fritz
  7. Diyi Yang
  8. Jared Kaplan

In Evaluation & Benchmarks

  1. Matei A. Zaharia
  2. Sahar Abdelnabi
  3. Caleb Ziems
  4. Peter Hase
  5. David Krueger
  6. James Y. Zou
  7. Thomas Liao
  8. Mario Fritz

In AI Ethics, Fairness & Society

  1. Matei A. Zaharia
  2. James Y. Zou
  3. Mario Fritz
  4. Diyi Yang
  5. Lingjiao Chen

Citations in the corpus