CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives

• URL: http://arxiv.org/abs/2504.10823v3
• Date: Fri, 26 Sep 2025 17:40:31 GMT
• Title: CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
• Authors: Ayoung Lee, Ryan Sungmo Kwon, Peter Railton, Lu Wang,
• Abstract summary: CLASH is a dataset consisting of 345 high-impact dilemmas along with 3,795 individual perspectives of diverse values.<n> CLASH enables the study of critical yet underexplored aspects of value-based decision-making processes.<n>Even strong proprietary models, such as GPT-5 and Claude-4-Sonnet, struggle with ambivalent decisions.
• Score: 3.7931130268412194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Navigating dilemmas involving conflicting values is challenging even for humans in high-stakes domains, let alone for AI, yet prior work has been limited to everyday scenarios. To close this gap, we introduce CLASH (Character perspective-based LLM Assessments in Situations with High-stakes), a meticulously curated dataset consisting of 345 high-impact dilemmas along with 3,795 individual perspectives of diverse values. CLASH enables the study of critical yet underexplored aspects of value-based decision-making processes, including understanding of decision ambivalence and psychological discomfort as well as capturing the temporal shifts of values in the perspectives of characters. By benchmarking 14 non-thinking and thinking models, we uncover several key findings. (1) Even strong proprietary models, such as GPT-5 and Claude-4-Sonnet, struggle with ambivalent decisions, achieving only 24.06 and 51.01 accuracy. (2) Although LLMs reasonably predict psychological discomfort, they do not adequately comprehend perspectives involving value shifts. (3) Cognitive behaviors that are effective in the math-solving and game strategy domains do not transfer to value reasoning. Instead, new failure patterns emerge, including early commitment and overcommitment. (4) The steerability of LLMs towards a given value is significantly correlated with their value preferences. (5) Finally, LLMs exhibit greater steerability when reasoning from a third-party perspective, although certain values (e.g., safety) benefit uniquely from first-person framing.

Related papers

• Can LLMs Capture Expert Uncertainty? A Comparative Analysis of Value Alignment in Ethnographic Qualitative Research [39.146761527401424]
  We evaluate large language models (LLMs) on the task of identifying the top three human values expressed in long-form interviews.<n>We compare their outputs to expert annotations, analyzing both performance and uncertainty patterns relative to the experts.
  arXiv  Detail & Related papers  (2026-03-05T07:38:37Z)
• Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation [51.19622266249408]
  MultiTrust-X is a benchmark for evaluating, analyzing, and mitigating the trustworthiness issues of MLLMs.<n>Based on the taxonomy, MultiTrust-X includes 32 tasks and 28 curated datasets.<n>Our experiments reveal significant vulnerabilities in current models.
  arXiv  Detail & Related papers  (2025-08-21T09:00:01Z)
• Reasoning Models Can be Easily Hacked by Fake Reasoning Bias [59.79548223686273]
  We introduce THEATER, a comprehensive benchmark to evaluate Reasoning Theater Bias (RTB)<n>We investigate six bias types including Simple Cues and Fake Chain-of-Thought.<n>We identify'shallow reasoning'-plausible but flawed arguments-as the most potent form of RTB.
  arXiv  Detail & Related papers  (2025-07-18T09:06:10Z)
• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? [81.49470136653665]
  We evaluate the robustness and expressiveness of value representations across three widely used probing strategies.<n>We show that the demographic context has little effect on the free-text generation, and the models' values only weakly correlate with their preference for value-based actions.
  arXiv  Detail & Related papers  (2025-07-17T18:56:41Z)
• Visual hallucination detection in large vision-language models via evidential conflict [24.465497252040294]
  Dempster-Shafer theory (DST)-based visual hallucination detection method for LVLMs through uncertainty estimation.<n>We propose to the best of our knowledge, the first Dempster-Shafer theory (DST)-based visual hallucination detection method for LVLMs through uncertainty estimation.
  arXiv  Detail & Related papers  (2025-06-24T11:03:10Z)
• Evaluating AI Alignment in Eleven LLMs through Output-Based Analysis and Human Benchmarking [0.0]
  Large language models (LLMs) are increasingly used in psychological research and practice, yet traditional benchmarks reveal little about the values they express in real interaction.<n>We introduce PAPERS, output-based evaluation of the values LLMs express.
  arXiv  Detail & Related papers  (2025-06-14T20:14:02Z)
• Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning [71.3533541927459]
  We propose a novel data selection paradigm termed Activation Reasoning Potential (RAP)<n>RAP identifies cognitive samples by estimating each sample's potential to stimulate genuine multi-modal reasoning.<n>Our RAP method consistently achieves superior performance using only 9.3% of the training data, while reducing computational costs by over 43%.
  arXiv  Detail & Related papers  (2025-06-05T08:40:24Z)
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time [52.230936493691985]
  We propose SITAlign, an inference framework that addresses the multifaceted nature of alignment by maximizing a primary objective while satisfying threshold-based constraints on secondary criteria.<n>We provide theoretical insights by deriving sub-optimality bounds of our satisficing based inference alignment approach.
  arXiv  Detail & Related papers  (2025-05-29T17:56:05Z)
• The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas [20.792208554628367]
  We introduce the Multi-step Moral Dilemmas dataset to evaluate the evolving moral judgments of LLMs across 3,302 five-stage dilemmas.<n>This framework enables a fine-grained, dynamic analysis of how LLMs adjust their moral reasoning across escalating dilemmas.<n>Our findings call for a shift toward dynamic, context-aware evaluation paradigms, paving the way for more human-aligned and value-sensitive development of LLMs.
  arXiv  Detail & Related papers  (2025-05-23T17:59:50Z)
• VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models [121.03333569013148]
  We introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories. These types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives. Most models score below 30% accuracy-only slightly above the 25% random baseline and far below the 51.4% achieved by humans.
  arXiv  Detail & Related papers  (2025-04-21T17:59:53Z)
• 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. 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)
• REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models [59.445672459851274]
  REVAL is a comprehensive benchmark designed to evaluate the textbfREliability and textbfVALue of Large Vision-Language Models.<n>REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability and Values.<n>We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro.
  arXiv  Detail & Related papers  (2025-03-20T07:54:35Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude [8.959468665453286]
  This study systematically evaluates how nine popular Large Language Models respond to ethical dilemmas involving protected attributes.<n>Across 50,400 trials spanning single and intersectional attribute combinations, we assess models' ethical preferences, sensitivity, stability, and clustering patterns.<n>Results reveal significant biases in protected attributes in all models, with differing preferences depending on model type and dilemma context.
  arXiv  Detail & Related papers  (2025-01-17T05:20:38Z)
• Value Compass Leaderboard: A Platform for Fundamental and Validated Evaluation of LLMs Values [76.70893269183684]
  Large Language Models (LLMs) achieve remarkable breakthroughs, aligning their values with humans has become imperative.<n>Existing evaluations focus narrowly on safety risks such as bias and toxicity.<n>Existing benchmarks are prone to data contamination.<n>The pluralistic nature of human values across individuals and cultures is largely ignored in measuring LLMs value alignment.
  arXiv  Detail & Related papers  (2025-01-13T05:53:56Z)
• Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens [30.083110119139793]
  We introduce textbfAbilityLens, a unified benchmark designed to evaluate MLLMs in six key perception abilities.<n>We identify the strengths and weaknesses of current main-stream MLLMs, highlighting stability patterns and revealing a notable performance gap between state-of-the-art open-source and closed-source models.
  arXiv  Detail & Related papers  (2024-11-22T04:41:20Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)
• CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses [34.77031649891843]
  We introduce CLAVE, a novel framework which integrates two complementary Large Language Models (LLMs) This dual-model approach enables calibration with any value systems using 100 human-labeled samples per value type. We present ValEval, a comprehensive dataset comprising 13k+ (text,value,label) 12+s across diverse domains, covering three major value systems.
  arXiv  Detail & Related papers  (2024-07-15T13:51:37Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• BeHonest: Benchmarking Honesty in Large Language Models [23.192389530727713]
  We introduce BeHonest, a pioneering benchmark specifically designed to assess honesty in Large Language Models. BeHonest evaluates three essential aspects of honesty: awareness of knowledge boundaries, avoidance of deceit, and consistency in responses. Our findings indicate that there is still significant room for improvement in the honesty of LLMs.
  arXiv  Detail & Related papers  (2024-06-19T06:46:59Z)
• Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context [5.361970694197912]
  This paper proposes a framework, grounded in behavioral economics, to evaluate the decision-making behaviors of large language models (LLMs) We estimate the degree of risk preference, probability weighting, and loss aversion in a context-free setting for three commercial LLMs: ChatGPT-4.0-Turbo, Claude-3-Opus, and Gemini-1.0-pro. Our results reveal that LLMs generally exhibit patterns similar to humans, such as risk aversion and loss aversion, with a tendency to overweight small probabilities.
  arXiv  Detail & Related papers  (2024-06-10T02:14:19Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs [60.61002524947733]
  Previous confidence elicitation methods rely on white-box access to internal model information or model fine-tuning. This leads to a growing need to explore the untapped area of black-box approaches for uncertainty estimation. We define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
  arXiv  Detail & Related papers  (2023-06-22T17:31:44Z)
• Revisiting the Reliability of Psychological Scales on Large Language Models [62.57981196992073]
  This study aims to determine the reliability of applying personality assessments to Large Language Models. Analysis of 2,500 settings per model, including GPT-3.5, GPT-4, Gemini-Pro, and LLaMA-3.1, reveals that various LLMs show consistency in responses to the Big Five Inventory.
  arXiv  Detail & Related papers  (2023-05-31T15:03:28Z)

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.