Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation

• URL: http://arxiv.org/abs/2607.25094v2
• Date: Wed, 29 Jul 2026 14:16:18 GMT
• Title: Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation
• Abstract summary: We evaluate the ability of large language models to recognize unspoken beliefs made through implicatures and to understand their updates through implicature cancellation.<n>We create the first expert-annotated implicature cancellation dataset, ImplicatureX, crowdsourced for human judgements of implicatures and their corresponding cancellations.
• Score: 24.054030923829387
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users. In this paper, we evaluate the ability of LLMs to recognize unspoken beliefs made through implicatures and to understand their updates through implicature cancellation: the pragmatic phenomenon whereby an utterance's implied meaning is weakened or negated. We create the first expert-annotated implicature cancellation dataset, ImplicatureX, crowdsourced for human judgements of implicatures and their corresponding cancellations. We find that LLM belief update understanding lags behind that of humans, especially in more naturally-occurring scenarios. Additional control experiments suggest that successes in LLM belief updates may stem in part from a reliance on prior beliefs, and that failures in belief updates may depend on their type and on their form. Overall, our study suggests that current LLMs have not yet reached human-level understanding of unspoken beliefs and belief updates. Code and data are available at https://github.com/cesare-spinoso/ImplicatureX.

Related papers

• Beliefs and Behavior in Language Models [15.920644659904903]
  Beliefs are often invoked to explain the behavior of large language models (LLMs)<n>We ask whether a single latent variable inferred from the LLMs' outputs -- interpreted as a degree of belief -- allows an observer to make interpretable predictions.<n>We find that highly capable models are usefully described as holding beliefs and that, generally, the predictability of model outputs based on an inferred latent belief tracks overall trends in model capability.
  arXiv  Detail & Related papers  (2026-09-07T19:56:02Z)
• Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It [7.192001578491251]
  We show that large language models (LLMs) exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information.<n>We find that the size and direction of the weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt"<n>Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models.
  arXiv  Detail & Related papers  (2026-08-18T14:06:26Z)
• Verbalizing LLMs' assumptions to explain and control sycophancy [62.927670321859495]
  LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment.<n>We present Verbalized Assumptions, a framework for eliciting these assumptions from LLMs.<n>Our work contributes a new understanding of assumptions as a mechanism for sycophancy.
  arXiv  Detail & Related papers  (2026-04-03T14:15:43Z)
• The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues [31.570641650845946]
  We introduce PUPPET, a theoretical taxonomy that focuses on the moral direction of hidden incentives in everyday, advice-giving contexts.<n>We provide an evaluation dataset of N=1,035 human-LLM interactions, where we measure users' belief shifts.<n>This work establishes a theoretically grounded and behaviorally validated foundation for AI social safety efforts.
  arXiv  Detail & Related papers  (2026-03-21T18:37:43Z)
• Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs [35.198654113796024]
  We show that social and linguistic factors known to influence accommodation in humans similarly affect accommodation in large language models.<n>We show that simple pragmatic interventions, such as adding the phrase "wait a minute", significantly improve performance on safety benchmarks.
  arXiv  Detail & Related papers  (2026-01-07T22:47:24Z)
• Incoherent Beliefs & Inconsistent Actions in Large Language Models [33.54139088666698]
  Real-world tasks and environments exhibit differences from the static datasets that large language models (LLMs) are typically evaluated on.<n>We examine two critical components of LLM performance: the ability of LLMs to coherently update their beliefs, and the extent to which the actions they take are consistent with those beliefs.<n>Our results highlight the difficulties of predicting LLM behavior in complex real-world settings.
  arXiv  Detail & Related papers  (2025-11-17T11:04:00Z)
• Are Large Language Models Sensitive to the Motives Behind Communication? [9.246336669308665]
  Large language models (LLMs) and AI agents process information inherently framed by humans' intentions and incentives.<n>For LLMs to be effective in the real world, they too must critically evaluate content by factoring in the motivations of the source.<n>We employ controlled experiments from cognitive science to verify that LLMs' behavior is consistent with rational models of learning from motivated testimony.<n>We find that LLMs' inferences do not track the rational models nearly as closely -- partly due to additional information that distracts them from vigilance-relevant considerations.
  arXiv  Detail & Related papers  (2025-10-22T15:35:00Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
  Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
  arXiv  Detail & Related papers  (2025-06-24T09:49:26Z)
• Belief Revision: The Adaptability of Large Language Models Reasoning [63.0281286287648]
  We introduce Belief-R, a new dataset designed to test LMs' belief revision ability when presented with new evidence. Inspired by how humans suppress prior inferences, this task assesses LMs within the newly proposed delta reasoning framework. We evaluate $sim$30 LMs across diverse prompting strategies and found that LMs generally struggle to appropriately revise their beliefs in response to new information.
  arXiv  Detail & Related papers  (2024-06-28T09:09:36Z)
• Towards Logically Consistent Language Models via Probabilistic Reasoning [14.317886666902822]
  Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. LLMs are prone to generate non-factual information and to contradict themselves when prompted to reason about beliefs of the world. We introduce a training objective that teaches a LLM to be consistent with external knowledge in the form of a set of facts and rules.
  arXiv  Detail & Related papers  (2024-04-19T12:23:57Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities.<n>If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information.<n>To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.