Belief Updating in LLMs

Theory of Mind (ToM) is central to social cognition and human-AI interaction, and Large Language Models (LLMs) have been used to help understand and represent ToM. However, most evaluations treat ToM as a static judgment at a single moment, primarily relying on tests of false beliefs. This overlooks a key dynamic dimension of ToM: the ability to represent, update, and retrieve others' beliefs over time. We investigate dynamic ToM as a temporally extended representational memory problem, asking whether LLMs can track belief trajectories across interactions rather than only inferring current beliefs. We introduce DToM-Track, an evaluation framework to investigate temporal belief reasoning in controlled multiturn conversations, testing the recall of beliefs held prior to an update, the inference of current beliefs, and the detection of belief change. Using LLMs as computational probes, we find a consistent asymmetry: models reliably infer an agent's current belief but struggle to maintain and retrieve prior belief states once updates occur. This pattern persists across LLM model families and scales, and is consistent with recency bias and interference effects well documented in cognitive science. These results suggest that tracking belief trajectories over time poses a distinct challenge beyond classical false-belief reasoning. By framing ToM as a problem of temporal representation and retrieval, this work connects ToM to core cognitive mechanisms of memory and interference and exposes the implications for LLM models of social reasoning in extended human-AI interactions.

Large language models (LLMs) are increasingly used to simulate human responses in behavioral research, yet it remains unclear when LLM-generated data support the same experimental inferences as human data. We evaluate this by directly comparing off-the-shelf LLM-generated responses with human responses from a canonical survey experiment on accuracy perception. Each human observation is converted into a structured prompt, and models generate a single 0--10 outcome variable without task-specific training; identical statistical analyses are applied to human and synthetic responses. We find that LLMs reproduce several directional effects observed in humans, but effect magnitudes and moderation patterns vary across models. Off-the-shelf LLMs therefore capture aggregate belief-updating patterns under controlled conditions but do not consistently match human-scale effects, clarifying when LLM-generated data can function as behavioral surrogates.

Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. From patient health logs tracking evolving vital signs to legal documents with superseding clauses, real-world applications routinely require models to retrieve specific values from streams of semantically similar, competing updates. We adapt classical interference paradigms from cognitive psychology to compare retroactive interference (RI; recalling initial values after updates) and proactive interference (PI; recalling recent values despite competing prior encodings) across 39 LLMs spanning 1B to 2.5T parameters. Every model exhibits the same pattern: PI causes substantially greater degradation than RI (d = 1.73), the opposite of the typical human finding where new information more readily disrupts old. Four lines of evidence indicate that RI and PI engage distinct mechanisms: model size predicts RI resistance but not PI; the two scores correlate only weakly; error analysis reveals qualitatively different failure profiles, with RI failures reflecting passive retrieval failure and PI failures reflecting active primacy intrusion; and hallucination rates remain below 1% in both conditions. An adaptive bootstrap design further shows that RI decays smoothly while PI collapses bimodally at high interference, consistent with gradual dilution versus winner-take-all attention dynamics. These findings characterize a systematic primacy bias in transformer attention, with implications for reliable deployment in settings where in-context information evolves over time.

Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentation, and verifier-guided revision, yet the structure of elicited probability transformations under these procedures remains poorly understood. We study externally elicited probability assignments over candidate answers and observe recurring approximate log-ratio relationships: $$\log \tilde q_t(i) = α_t \left( \log q_t(i) + \log b_t(i) \right) + c_t,$$ where $q_t$ and $\tilde q_t$ are pre- and post-elicitation probabilities, $b_t$ is an externally constructed evidence signal, and $α_t$ is an empirical descriptor of the prompting configuration. Across 4,975 reasoning problems from GPQA Diamond, TheoremQA, MMLU-Pro, and ARC-Challenge, evaluated on multiple instruction-tuned model families, we observe approximate log-ratio relationships with mean $R^2 \approx 0.76$ over about $1.3 \times 10^5$ candidate-level observations. Coefficients vary across elicitation settings, but qualitatively similar relationships persist across evaluated conditions. Robustness analyses using alternative statistical representations, prompting configurations, held-out evaluation, and token-level log-probabilities suggest that the observed structure is not tied to one prompting procedure or probability estimation method. The main contribution is not the algebraic form itself, which is related to generalized Bayesian updating and probability-transformation frameworks, but the empirical observation that diverse inference-time prompting pipelines repeatedly exhibit reproducible log-ratio structure under controlled conditions. The framework provides a protocol-sensitive perspective for analyzing calibration, evidence amplification, uncertainty propagation, and interaction sensitivity in inference-time LLM pipelines.

LLMs are widely used in knowledge-intensive tasks where the same fact may be revised multiple times within context. Unlike prior work focusing on one-shot updates or single conflicts, multi-update scenarios contain multiple historically valid versions that compete at retrieval, yet remain underexplored. This challenge resembles the AB-AC interference paradigm in cognitive psychology: when the same cue A is successively associated with B and C, the old and new associations compete during retrieval, leading to bias. Inspired by this, we introduce a Dynamic Knowledge Instance (DKI) evaluation framework, modeling multi-updates of the same fact as a cue paired with a sequence of updated values, and assess models via endpoint probing of the earliest (initial) and latest (current) states. Across diverse LLMs, we observe that retrieval bias intensifies as updates increase, earliest-state accuracy stays high while latest-state accuracy drops substantially. Diagnostic analyses of attention, hidden-state similarity, and output logits further reveal that these signals become flatter and weakly discriminative on errors, providing little stable basis for identifying the latest update. Finally, cognitively inspired heuristic intervention strategies yield only modest gains and do not eliminate the bias. Our results reveal a persistent challenge in tracking and following knowledge updates in long contexts.

Large Language Models (LLMs) are increasingly employed in various question-answering tasks. However, recent studies showcase that LLMs are susceptible to persuasion and could adopt counterfactual beliefs. We present a systematic evaluation of LLM susceptibility to persuasion under the Source--Message--Channel--Receiver (SMCR) communication framework. Across six mainstream Large Language Models (LLMs) and three domains (factual knowledge, medical QA, and social bias), we analyze how different persuasive strategies influence stated belief stability over multiple interaction turns. We further examine whether verbalized confidence prompting (i.e., eliciting self-reported confidence scores) affects resistance to persuasion. Results show that the smallest model (Llama 3.2-3B) exhibits extreme compliance, with 82.5% of belief changes occurring at the first persuasive turn (average end turn of 1.1--1.4). Contrary to expectations, verbalized confidence prompting increases vulnerability by accelerating belief erosion rather than enhancing robustness. Finally, an exploratory study of adversarial fine-tuning reveals highly model-dependent effectiveness: GPT-4o-mini achieves near-complete robustness (98.6%), and Mistral~7B improves substantially (35.7% $\rightarrow$ 79.3%), but Llama models remain highly susceptible ($<$14% RQ1) even when fine-tuned on their own failure cases. Together, these findings highlight substantial model-dependent limits of current robustness interventions and offer guidance for developing more trustworthy LLMs.

Modeling opinion change through social interactions is important for understanding polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior (e.g., premature convergence) and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels. We instantiate digital-twin RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. Across group-generalization tests with unseen participant groups and topic-generalization tests with unseen discussion topics, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves stance prediction of individuals and convergence prediction at the group level, though discrepancies in opinion change and belief updating remain. The dataset and benchmark website are publicly available.