Summary of A Dataset Of Questions on Decision-theoretic Reasoning in Newcomb-like Problems, by Caspar Oesterheld and Emery Cooper and Miles Kodama and Linh Chi Nguyen and Ethan Perez
A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
by Caspar Oesterheld, Emery Cooper, Miles Kodama, Linh Chi Nguyen, Ethan Perez
First submitted to arxiv on: 15 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a new dataset of natural-language questions focused on decision theory in Newcomb-like problems. These types of problems involve complex decision-making processes where agents interact with each other, requiring them to reason about similar agents’ actions. Evaluating large language model (LLM) reasoning abilities in this domain is crucial as LLMs will increasingly interact with each other in Newcomb-like scenarios. The study explores various ways of reasoning about these problems, which may lead to improved cooperation between models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this paper creates a new dataset of questions that helps computers make better decisions when interacting with each other. Right now, computer programs can’t always work together effectively because they don’t understand how the other program will behave. This new dataset is important because it allows researchers to test if these programs can learn to cooperate and make better choices. |
Keywords
» Artificial intelligence » Large language model
