# Beliefs and Behavior in Language Models

arXiv: https://arxiv.org/abs/2609.07943 · HTML: https://mlsanity.com/paper/2609.07943/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [The Debate Over Understanding in AI's Large Language Models](https://mlsanity.com/paper/2210.13966/) (2022)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems](https://mlsanity.com/paper/2503.03750/) (2025)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Incoherent Probability Judgments in Large Language Models](https://mlsanity.com/paper/2401.16646/) (2024)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [Thought Branches: Interpreting LLM Reasoning Requires Resampling](https://mlsanity.com/paper/2510.27484/) (2025)
- [Does ChatGPT Have a Mind?](https://mlsanity.com/paper/2407.11015/) (2024)
- [Thinking beyond the anthropomorphic paradigm benefits LLM research](https://mlsanity.com/paper/2502.09192/) (2025)
- [When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs](https://mlsanity.com/paper/2602.06286/) (2026)
- [Where is the Mind? Persona Vectors and LLM Individuation](https://mlsanity.com/paper/2604.17031/) (2026)
- [LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs](https://mlsanity.com/paper/2605.06915/) (2026)
- [Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions](https://mlsanity.com/paper/2511.13240/) (2025)

## Built on by (most cited first, 1 of 1)

- [Diagnosing and Improving Probabilistic Reasoning in Large Language Models](https://mlsanity.com/paper/2609.38005/) (2026)

## Abstract (arXiv)

There is significant uncertainty about whether abstractions like beliefs or desires usefully describe the behavior of large language models (LLMs). In addition to the inherent scientific interest of this question, these latent quantities are often invoked to explain the behavior of LLMs to users or to define and evaluate harmful behaviors which are relative to intent. Nevertheless, we currently lack a means to systematically test whether concepts like "belief" are well-applied to LLMs, and hence whether they are likely to be fruitful ingredients of attempts to align models with human interests. We propose an approach for empirically studying such questions, asking whether a single latent variable inferred from the LLMs' outputs -- interpreted as a degree of belief -- allows an observer to make interpretable predictions of how the LLMs' will respond to new prompts. 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. Building on these findings, we provide empirical strategies to study how beliefs in LLMs can be measured, the extent to which LLMs comply with instructed decision rules or payoffs, and how beliefs evolve within individual instances of an LLM over the course of reasoning.