Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models

• URL: http://arxiv.org/abs/2505.19621v1
• Date: Mon, 26 May 2025 07:41:21 GMT
• Title: Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
• Authors: George Kour, Itay Nakash, Ateret Anaby-Tavor, Michal Shmueli-Scheuer,
• Abstract summary: Large Language Models (LLMs) are increasingly integrated into human life and increasingly influence decision-making.<n>It's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs.<n>This paper presents the Preference, Opinion, and Belief survey (POBs) to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains.
• Score: 6.9347404883379316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models (LLMs) become deeply integrated into human life and increasingly influence decision-making, it's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs. These tendencies may stem from biases within the models, which may shape their behavior, influence the advice and recommendations they offer to users, and potentially reinforce certain viewpoints. This paper presents the Preference, Opinion, and Belief survey (POBs), a benchmark developed to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains. We applied our benchmark to evaluate leading open- and closed-source LLMs, measuring desired properties such as reliability, neutrality, and consistency. In addition, we investigated the effect of increasing the test-time compute, through reasoning and self-reflection mechanisms, on those metrics. While effective in other tasks, our results show that these mechanisms offer only limited gains in our domain. Furthermore, we reveal that newer model versions are becoming less consistent and more biased toward specific viewpoints, highlighting a blind spot and a concerning trend. POBS: https://ibm.github.io/POBS

Related papers

• Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offs [22.588557390720236]
  We characterize subjectivity of individuals on social media and infer their moral judgments using Large Language Models.<n>We propose a framework, SOLAR, that observes value conflicts and trade-offs in the user-generated texts to better represent subjective ground of individuals.
  arXiv  Detail & Related papers  (2025-04-17T04:20:05Z)
• Investigating the Impact of LLM Personality on Cognitive Bias Manifestation in Automated Decision-Making Tasks [4.65004369765875]
  Personality traits play a crucial role in either amplifying or reducing biases.<n>Conscientiousness and Agreeableness may generally enhance the efficacy of bias mitigation strategies.
  arXiv  Detail & Related papers  (2025-02-20T03:15:54Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Persuasion with Large Language Models: a Survey [49.86930318312291]
  Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
  arXiv  Detail & Related papers  (2024-11-11T10:05:52Z)
• 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)
• When Prompting Fails to Sway: Inertia in Moral and Value Judgments of Large Language Models [4.906478894661688]
  Large Language Models (LLMs) exhibit non-deterministic behavior, and prompting has emerged as a primary method for steering their outputs toward desired directions.<n>One popular strategy involves assigning a specific "persona" to the model to induce more varied and context-sensitive responses, akin to the diversity found in human perspectives.<n>Our experiments demonstrate that LLMs maintain consistent value orientations.<n>In particular, we observe a persistent inertia in their responses, where certain moral and value dimensions, especially harm avoidance and fairness, remain distinctly skewed in one direction despite varied persona settings.
  arXiv  Detail & Related papers  (2024-08-16T23:24:10Z)
• ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models [53.00812898384698]
  We argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. We propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars -- Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.
  arXiv  Detail & Related papers  (2024-05-28T22:45:28Z)
• More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness [24.843692458375436]
  This study investigates how models aligned with general-purpose preference data perform across five trustworthiness verticals.<n>Our results demonstrate that RLHF on human preferences doesn't automatically guarantee trustworthiness, and reverse effects are often observed.<n>We propose to adapt efficient influence function based data attribution methods to the RLHF setting to better understand the influence of fine-tuning data on individual trustworthiness benchmarks.
  arXiv  Detail & Related papers  (2024-04-29T17:00:53Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) are used to automate decision-making tasks.<n>In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention.<n>We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types.<n>These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models [83.30078426829627]
  Large language models (LLMs) have gained popularity and are being widely adopted by a large user community. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
  arXiv  Detail & Related papers  (2023-12-11T12:02:14Z)

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.