Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models

• URL: http://arxiv.org/abs/2402.16786v2
• Date: Wed, 5 Jun 2024 10:17:53 GMT
• Title: Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
• Authors: Paul Röttger, Valentin Hofmann, Valentina Pyatkin, Musashi Hinck, Hannah Rose Kirk, Hinrich Schütze, Dirk Hovy,
• Abstract summary: 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.
• Score: 61.45529177682614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Much recent work seeks to evaluate values and opinions in large language models (LLMs) using multiple-choice surveys and questionnaires. Most of this work is motivated by concerns around real-world LLM applications. For example, politically-biased LLMs may subtly influence society when they are used by millions of people. Such real-world concerns, however, stand in stark contrast to the artificiality of current evaluations: real users do not typically ask LLMs survey questions. Motivated by this discrepancy, we challenge the prevailing constrained evaluation paradigm for values and opinions in LLMs and explore more realistic unconstrained evaluations. As a case study, we focus on the popular Political Compass Test (PCT). In a systematic review, we find that most prior work using the PCT forces models to comply with the PCT's multiple-choice format. We show that models give substantively different answers when not forced; that answers change depending on how models are forced; and that answers lack paraphrase robustness. Then, we demonstrate that models give different answers yet again in a more realistic open-ended answer setting. We distill these findings into recommendations and open challenges in evaluating values and opinions in LLMs.

Related papers

• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ? [22.0383367888756]
  Large language models (LLMs) inherit biases from their training data and alignment processes, influencing their responses in subtle ways. We introduce a novel approach where two instances of an LLM engage in self-debate, arguing opposing viewpoints to persuade a neutral version of the model. We evaluate how firmly biases hold and whether models are susceptible to reinforcing misinformation or shifting to harmful viewpoints.
  arXiv  Detail & Related papers  (2024-10-17T13:06:02Z)
• DebateQA: Evaluating Question Answering on Debatable Knowledge [13.199937786970027]
  We introduce DebateQA, a dataset of 2,941 debatable questions. We develop two metrics: Perspective Diversity and Dispute Awareness. Using DebateQA with two metrics, we assess 12 popular large language models.
  arXiv  Detail & Related papers  (2024-08-02T17:54:34Z)
• GermanPartiesQA: Benchmarking Commercial Large Language Models for Political Bias and Sycophancy [20.06753067241866]
  We evaluate and compare the alignment of six LLMs by OpenAI, Anthropic, and Cohere with German party positions. We conduct our prompt experiment for which we use the benchmark and sociodemographic data of leading German parliamentarians.
  arXiv  Detail & Related papers  (2024-07-25T13:04:25Z)
• 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)
• Whose Side Are You On? Investigating the Political Stance of Large Language Models [56.883423489203786]
  We investigate the political orientation of Large Language Models (LLMs) across a spectrum of eight polarizing topics. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. The findings suggest that users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.
  arXiv  Detail & Related papers  (2024-03-15T04:02:24Z)
• Exploring Value Biases: How LLMs Deviate Towards the Ideal [57.99044181599786]
  Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact. We show that value bias is strong in LLMs across different categories, similar to the results found in human studies.
  arXiv  Detail & Related papers  (2024-02-16T18:28:43Z)
• Do LLMs exhibit human-like response biases? A case study in survey design [66.1850490474361]
  We investigate the extent to which large language models (LLMs) reflect human response biases, if at all. We design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior.
  arXiv  Detail & Related papers  (2023-11-07T15:40:43Z)
• PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations [10.709365940160685]
  Modern large language models (LLMs) are hard to evaluate and compare automatically. We propose a peer rank (PR) algorithm that takes into account each peer LLM's pairwise preferences of all answer pairs. We find that our approaches achieve higher accuracy and align better with human judgments.
  arXiv  Detail & Related papers  (2023-07-06T04:05:44Z)
• 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.