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

• URL: http://arxiv.org/abs/2411.10588v2
• Date: Thu, 21 Nov 2024 00:24:36 GMT
• Title: A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
• Authors: Caspar Oesterheld, Emery Cooper, Miles Kodama, Linh Chi Nguyen, Ethan Perez,
• Abstract summary: We introduce a dataset of natural-language questions in the decision theory of so-called Newcomb-like problems. Some ways of reasoning about Newcomb-like problems may allow for greater cooperation between models.
• Score: 10.826981264871655
• License:
• Abstract: 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.

Related papers

• Can Model Uncertainty Function as a Proxy for Multiple-Choice Question Item Difficulty? [12.638577140117702]
  We leverage an aspect of generative large models which might be seen as a weakness when answering questions. We explore correlations between two different metrics of uncertainty, and the actual student response distribution.
  arXiv  Detail & Related papers  (2024-07-07T10:48:04Z)
• Analyzing Human Questioning Behavior and Causal Curiosity through Natural Queries [91.70689724416698]
  We present NatQuest, a collection of 13,500 naturally occurring questions from three diverse sources. Our analysis reveals a significant presence of causal questions (up to 42%) within the dataset.
  arXiv  Detail & Related papers  (2024-05-30T17:55:28Z)
• ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos [53.92440577914417]
  ACQUIRED consists of 3.9K annotated videos, encompassing a wide range of event types and incorporating both first and third-person viewpoints. Each video is annotated with questions that span three distinct dimensions of reasoning, including physical, social, and temporal. We benchmark our dataset against several state-of-the-art language-only and multimodal models and experimental results demonstrate a significant performance gap.
  arXiv  Detail & Related papers  (2023-11-02T22:17:03Z)
• A Conceptual Model for End-to-End Causal Discovery in Knowledge Tracing [8.049552839071918]
  We take a preliminary step towards solving the problem of causal discovery in knowledge tracing. Our solution placed among the top entries in Task 3 of the NeurIPS 2022 Challenge on Causal Insights for Learning Paths in Education.
  arXiv  Detail & Related papers  (2023-05-11T21:20:29Z)
• Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning [30.392986232906107]
  We propose an integral framework consisting of a principled object factorization method and a novel neural module network. Our factorization method decomposes objects based on their key characteristics, and automatically derives prototypes that represent a wide range of objects. With these prototypes encoding important semantics, the proposed network then correlates objects by measuring their similarity on a common semantic space. It is capable of answering questions with diverse objects regardless of their availability during training, and overcoming the issues of biased question-answer distributions.
  arXiv  Detail & Related papers  (2023-03-18T19:37:28Z)
• Modeling Transformative AI Risks (MTAIR) Project -- Summary Report [0.0]
  This report builds on an earlier diagram by Cottier and Shah which laid out some of the crucial disagreements ("cruxes") visually, with some explanation. The model starts with a discussion of reasoning via analogies and general prior beliefs about artificial intelligence. It lays out a model of different paths and enabling technologies for high-level machine intelligence, and a model of how advances in the capabilities of these systems might proceed. The model also looks specifically at the question of learned optimization, and whether machine learning systems will create mesa-optimizers.
  arXiv  Detail & Related papers  (2022-06-19T09:11:23Z)
• MetaQA: Combining Expert Agents for Multi-Skill Question Answering [49.35261724460689]
  We argue that despite the promising results of multi-dataset models, some domains or QA formats might require specific architectures. We propose to combine expert agents with a novel, flexible, and training-efficient architecture that considers questions, answer predictions, and answer-prediction confidence scores.
  arXiv  Detail & Related papers  (2021-12-03T14:05:52Z)
• Learning with Instance Bundles for Reading Comprehension [61.823444215188296]
  We introduce new supervision techniques that compare question-answer scores across multiple related instances. Specifically, we normalize these scores across various neighborhoods of closely contrasting questions and/or answers. We empirically demonstrate the effectiveness of training with instance bundles on two datasets.
  arXiv  Detail & Related papers  (2021-04-18T06:17:54Z)
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics [20.447000858907646]
  The capability of imagining internally with a mental model of the world is vitally important for human cognition. We propose Causal World Models (CWMs) that allow unsupervised modeling of relationships between the intervened and alternative futures. We show reductions in complexity sample for reinforcement learning tasks and improvements in counterfactual physical reasoning.
  arXiv  Detail & Related papers  (2020-12-28T13:44:36Z)
• Match$^2$: A Matching over Matching Model for Similar Question Identification [74.7142127303489]
  Community Question Answering (CQA) has become a primary means for people to acquire knowledge, where people are free to ask questions or submit answers. Similar question identification becomes a core task in CQA which aims to find a similar question from the archived repository whenever a new question is asked. It has long been a challenge to properly measure the similarity between two questions due to the inherent variation of natural language, i.e., there could be different ways to ask a same question or different questions sharing similar expressions. Traditional methods typically take a one-side usage, which leverages the answer as some expanded representation of the
  arXiv  Detail & Related papers  (2020-06-21T05:59:34Z)
• SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions [66.86887670416193]
  We show that state-of-the-art VQA models have comparable performance in answering perception and reasoning questions, but suffer from consistency problems. To address this shortcoming, we propose an approach called Sub-Question-aware Network Tuning (SQuINT) We show that SQuINT improves model consistency by 5%, also marginally improving performance on the Reasoning questions in VQA, while also displaying better attention maps.
  arXiv  Detail & Related papers  (2020-01-20T01:02:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.