Towards Measuring the Representation of Subjective Global Opinions in Language Models

• URL: http://arxiv.org/abs/2306.16388v2
• Date: Fri, 12 Apr 2024 00:05:53 GMT
• Title: Towards Measuring the Representation of Subjective Global Opinions in Language Models
• Authors: Esin Durmus, Karina Nguyen, Thomas I. Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, Liane Lovitt, Sam McCandlish, Orowa Sikder, Alex Tamkin, Janel Thamkul, Jared Kaplan, Jack Clark, Deep Ganguli,
• Abstract summary: Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. We develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We release our dataset for others to use and build on.
• Score: 26.999751306332165
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinions model-generated responses are more similar to. We first build a dataset, GlobalOpinionQA, comprised of questions and answers from cross-national surveys designed to capture diverse opinions on global issues across different countries. Next, we define a metric that quantifies the similarity between LLM-generated survey responses and human responses, conditioned on country. With our framework, we run three experiments on an LLM trained to be helpful, honest, and harmless with Constitutional AI. By default, LLM responses tend to be more similar to the opinions of certain populations, such as those from the USA, and some European and South American countries, highlighting the potential for biases. When we prompt the model to consider a particular country's perspective, responses shift to be more similar to the opinions of the prompted populations, but can reflect harmful cultural stereotypes. When we translate GlobalOpinionQA questions to a target language, the model's responses do not necessarily become the most similar to the opinions of speakers of those languages. We release our dataset for others to use and build on. Our data is at https://huggingface.co/datasets/Anthropic/llm_global_opinions. We also provide an interactive visualization at https://llmglobalvalues.anthropic.com.

Related papers

• Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion [45.84205238554709]
  We generate a synthetic sample of personas matching the individual characteristics of the 2017 German Longitudinal Election Study respondents. We ask the LLM GPT-3.5 to predict each respondent's vote choice and compare these predictions to the survey-based estimates. We find that GPT-3.5 does not predict citizens' vote choice accurately, exhibiting a bias towards the Green and Left parties.
  arXiv  Detail & Related papers  (2024-07-11T14:52:18Z)
• Vision-Language Models under Cultural and Inclusive Considerations [53.614528867159706]
  Large vision-language models (VLMs) can assist visually impaired people by describing images from their daily lives. Current evaluation datasets may not reflect diverse cultural user backgrounds or the situational context of this use case. We create a survey to determine caption preferences and propose a culture-centric evaluation benchmark by filtering VizWiz, an existing dataset with images taken by people who are blind. We then evaluate several VLMs, investigating their reliability as visual assistants in a culturally diverse setting.
  arXiv  Detail & Related papers  (2024-07-08T17:50:00Z)
• Language Model Alignment in Multilingual Trolley Problems [138.5684081822807]
  Building on the Moral Machine experiment, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP. Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions. We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems.
  arXiv  Detail & Related papers  (2024-07-02T14:02:53Z)
• CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models [59.22460740026037]
  "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset is designed to evaluate the social and cultural variation of Large Language Models (LLMs) We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy.
  arXiv  Detail & Related papers  (2024-05-22T20:19:10Z)
• The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models [67.38144169029617]
  We introduce PRISM, a new dataset which maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries. PRISM contributes (i) wide geographic and demographic participation in human feedback data; (ii) two census-representative samples for understanding collective welfare (UK and US); and (iii) individualised feedback where every rating is linked to a detailed participant profile.
  arXiv  Detail & Related papers  (2024-04-24T17:51:36Z)
• Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models [61.45529177682614]
  We challenge the prevailing constrained evaluation paradigm for values and opinions in large language models. We show that models give substantively different answers when not forced. We distill these findings into recommendations and open challenges in evaluating values and opinions in LLMs.
  arXiv  Detail & Related papers  (2024-02-26T18:00:49Z)
• This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models [40.61046400448044]
  We show that large language models (LLM) recall certain geographical knowledge inconsistently when queried in different languages. As a targeted case study, we consider territorial disputes, an inherently controversial and multilingual task. We propose a suite of evaluation metrics to precisely quantify bias and consistency in responses across different languages.
  arXiv  Detail & Related papers  (2023-05-24T01:16:17Z)
• Whose Opinions Do Language Models Reflect? [88.35520051971538]
  We investigate the opinions reflected by language models (LMs) by leveraging high-quality public opinion polls and their associated human responses. We find substantial misalignment between the views reflected by current LMs and those of US demographic groups. Our analysis confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs.
  arXiv  Detail & Related papers  (2023-03-30T17:17:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.