# Dutch Books for Language Models

arXiv: https://arxiv.org/abs/2609.02797 · HTML: https://mlsanity.com/paper/2609.02797/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief](https://mlsanity.com/paper/2109.14723/) (2021)
- [Evaluating Superhuman Models with Consistency Checks](https://mlsanity.com/paper/2306.09983/) (2023)
- [What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models](https://mlsanity.com/paper/2507.06952/) (2025)
- [Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference](https://mlsanity.com/paper/2211.11875/) (2022)
- [Assessing Look-Ahead Bias in Stock Return Predictions Generated By GPT Sentiment Analysis](https://mlsanity.com/paper/2309.17322/) (2023)
- [Consistency Checks for Language Model Forecasters](https://mlsanity.com/paper/2412.18544/) (2024)
- [PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data](https://mlsanity.com/paper/2604.14199/) (2026)
- [Poly-EPO: Training Exploratory Reasoning Models](https://mlsanity.com/paper/2604.17654/) (2026)
- [Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems](https://mlsanity.com/paper/2608.05015/) (2026)
- [Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations](https://mlsanity.com/paper/2605.04764/) (2026)
- [Position: It's Time to Optimize LLMs for Self-Consistency](https://mlsanity.com/paper/2608.05188/) (2026)

## Built on by (most cited first, 3 of 3)

- [Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?](https://mlsanity.com/paper/2609.33209/) (2026)
- [Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces](https://mlsanity.com/paper/2609.37470/) (2026)
- [Bayesian Intelligence from the Outside](https://mlsanity.com/paper/2609.14724/) (2026)

## Abstract (arXiv)

People increasingly use language models to support life decisions. Many such decisions involve a probabilistic forecast: How likely is a major life event, a natural disaster, or an economic outcome? Users of language models may implicitly trust that these forecasts fall out of a coherent world model. In this paper, we evaluate the coherence of language model probabilistic forecasts through a procedure that builds on a theorem due to de Finetti. We elicit forecasts from language models across events generated from stock returns data. We then use linear programs to compute the largest Dutch-book profit - the profit an arbitrageur could guarantee by betting against model-generated probabilities - which we use as a measure of incoherence. Our procedure does not require outcome labels, so we can evaluate coherence even in settings where outcomes are not observed or have not yet resolved. We find substantial evidence of incoherence in language model forecasts. Such incoherence increases when there are richer logical relationships between events, and irrelevant contextual details can increase incoherence by an order of magnitude. We conclude by discussing how alternative training strategies may improve probabilistic coherence.