How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models

• URL: http://arxiv.org/abs/2608.26327v1
• Date: Wed, 26 Aug 2026 19:00:41 GMT
• Title: How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models
• Abstract summary: We present a systematic cross-model evaluation using a word-to-number mapping task grounded in established human benchmarks.<n>Eleven uncertainty expressions were presented to 19 models under two conditions, forced single-number response and explanation elicitation.<n>Models show a systematic upward bias for negative expressions such as unlikely'' and improbable''
• Score: 1.435579512127234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across models (or match human perceptions of uncertainty) remains unknown. We present a systematic cross-model evaluation using a word-to-number mapping task grounded in established human benchmarks. Eleven uncertainty expressions were presented to 19 models under two conditions, forced single-number response and explanation elicitation, alongside a novel bidirectional roundtrip test of internal consistency. LLMs track the human benchmark with surprising fidelity: word ordering is preserved, three anchor points are recovered, and ``possible'' shows the highest variance and cross-model disagreement of any expression tested, consistent with its documented bimodal interpretation in humans. However, models show a systematic upward bias for negative expressions such as ``unlikely'' and ``improbable.'' Explanation elicitation reduces within-model variance while increasing between-model divergence, stabilizing individual models at the cost of inter-model consensus, and the roundtrip experiment reveals clear stratification, with frontier models maintaining coherent bidirectional representations. LLMs thus reproduce the structure of human verbal probability cognition, including its biases, while diverging systematically at the negative end---with implications for any setting where humans and models exchange probabilistic language.

Related papers

• Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis [57.78407973423517]
  We advocate uncertainty-aware subjectivity analysis, where models are expected to make predictions while expressing uncertainty that reflects human disagreement.<n>To operationalize this perspective, we propose a two-phase Disagreement Perception and Uncertainty Alignment framework.<n> Experiments on three subjectivity analysis tasks show that DPUA preserves task performance while better aligning model uncertainty with human disagreement.
  arXiv  Detail & Related papers  (2026-05-11T11:52:58Z)
• Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains [0.0]
  We extend surprisal-based evaluation from binary grammaticality to ordinal-scaled classification and scoring tasks.<n>Rather than asking models to generate answers, we measure the information-theoretic "surprise"<n>We explore this framework across four domains: social-ecological-technological systems classification, causal statement identification (binary and scaled), figurative language detection, and deductive qualitative coding.
  arXiv  Detail & Related papers  (2026-03-15T14:31:00Z)
• Mastering Negation: Boosting Grounding Models via Grouped Opposition-Based Learning [87.15765427638195]
  We introduce D-Negation, a new dataset that provides objects annotated with both positive and negative semantic descriptions.<n>We propose a grouped opposition-based learning framework that learns negation-aware representations from limited samples.<n>By fine-tuning fewer than 10 percent of the model parameters, our approach achieves improvements of up to 4.4 mAP and 5.7 mAP on positive and negative semantic evaluations.
  arXiv  Detail & Related papers  (2026-03-13T03:21:48Z)
• Measuring Language Model Hallucinations Through Distributional Correctness [7.106986689736826]
  A novel evaluation metric, the Distributional Correctness Score (DCS), is introduced to solve this problem.<n>DCS distinguishes between harmful overconfidence in wrong answers and uncertainty expressed through abstention, providing scores in an interpretable default range.<n>DCS is demonstrated to offer a more nuanced and aligned evaluation paradigm that incentivises models to express genuine uncertainty rather than guessing.
  arXiv  Detail & Related papers  (2025-10-05T17:50:42Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [58.32070787537946]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness [68.69369585600698]
  Deep learning models often suffer from a lack of interpretability due to polysemanticity. Recent advances in monosemanticity, where neurons correspond to consistent and distinct semantics, have significantly improved interpretability. We show that monosemantic features not only enhance interpretability but also bring concrete gains in model performance.
  arXiv  Detail & Related papers  (2024-10-27T18:03:20Z)
• CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models [16.436592723426305]
  It is unclear whether language models produce the same value for different ways of assigning joint probabilities to word spans. Our work introduces a novel framework, ConTestS, involving statistical tests to assess score consistency across interchangeable completion and conditioning orders.
  arXiv  Detail & Related papers  (2024-09-30T06:24:43Z)
• How often are errors in natural language reasoning due to paraphrastic variability? [29.079188032623605]
  We propose a metric for evaluating the paraphrastic consistency of natural language reasoning models. We mathematically connect this metric to the proportion of a model's variance in correctness attributable to paraphrasing. We collect ParaNLU, a dataset of 7,782 human-written and validated paraphrased reasoning problems.
  arXiv  Detail & Related papers  (2024-04-17T20:11:32Z)
• Incoherent Probability Judgments in Large Language Models [4.307483901449801]
  We assess the coherence of probability judgments made by autoregressive Large Language Models (LLMs)<n>Our results show that the judgments produced by these models are often incoherent, displaying human-like systematic deviations from the rules of probability theory.
  arXiv  Detail & Related papers  (2024-01-30T00:40:49Z)
• Tailoring Language Generation Models under Total Variation Distance [55.89964205594829]
  The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. We develop practical bounds to apply it to language generation. We introduce the TaiLr objective that balances the tradeoff of estimating TVD.
  arXiv  Detail & Related papers  (2023-02-26T16:32:52Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)

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.