# A dataset of questions on decision-theoretic reasoning in Newcomb-like problems

arXiv: https://arxiv.org/abs/2411.10588 · HTML: https://mlsanity.com/paper/2411.10588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 21 of its 108 references that are in the map.
- First posted on arXiv 15 Nov 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 21 of 21)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [AI safety via debate](https://mlsanity.com/paper/1805.00899/) (2018)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [Preventing Language Models From Hiding Their Reasoning](https://mlsanity.com/paper/2310.18512/) (2023)
- [Large Language Models as Superpositions of Cultural Perspectives](https://mlsanity.com/paper/2307.07870/) (2023)
- [Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic](https://mlsanity.com/paper/1401.5577/) (2014)
- [Towards the Scalable Evaluation of Cooperativeness in Language Models](https://mlsanity.com/paper/2303.13360/) (2023)
- [Conditioning Predictive Models: Risks and Strategies](https://mlsanity.com/paper/2302.00805/) (2023)
- [Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT](https://mlsanity.com/paper/2407.21058/) (2024)
- [Recursive Joint Simulation in Games](https://mlsanity.com/paper/2402.08128/) (2024)
- [Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models](https://mlsanity.com/paper/2406.14986/) (2024)
- [Toward Idealized Decision Theory](https://mlsanity.com/paper/1507.01986/) (2015)
- [Reinforcement Learning in Conflicting Environments for Autonomous Vehicles](https://mlsanity.com/paper/1610.07089/) (2016)
- [Can CDT rationalise the ex ante optimal policy via modified anthropics?](https://mlsanity.com/paper/2411.04462/) (2024)

## Built on by (most cited first, 4 of 4)

- [A dataset of rated conceptual arguments](https://mlsanity.com/paper/2607.27499/) (2026)
- [A game theory for foundation models shows new paths to rational cooperation through similarity inference](https://mlsanity.com/paper/2608.03958/) (2026)
- [Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation](https://mlsanity.com/paper/2608.12125/) (2026)
- [Character Training for Risk-Averse Agents](https://mlsanity.com/paper/2609.38093/) (2026)

## Abstract (arXiv)

We introduce a dataset of natural-language questions in the decision theory of so-called Newcomb-like problems. Newcomb-like problems include, for instance, decision problems in which an agent interacts with a similar other agent, and thus has to reason about the fact that the other agent will likely reason in similar ways. Evaluating LLM reasoning about Newcomb-like problems is important because interactions between foundation-model-based agents will often be Newcomb-like. Some ways of reasoning about Newcomb-like problems may allow for greater cooperation between models. Our dataset contains both capabilities questions (i.e., questions with a unique, uncontroversially correct answer) and attitude questions (i.e., questions about which decision theorists would disagree). We use our dataset for an investigation of decision-theoretical capabilities and expressed attitudes and their interplay in existing models (different models by OpenAI, Anthropic, Meta, GDM, Reka, etc.), as well as models under simple prompt-based interventions. We find, among other things, that attitudes vary significantly between existing models; that high capabilities are associated with attitudes more favorable toward so-called evidential decision theory; and that attitudes are consistent across different types of questions.