BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Published: 26 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 Datasets and Benchmarks PosterEveryoneRevisionsBibTeX
Keywords: natural language reasoning, defeasible reasoning, large language models
TL;DR: We create a dataset for natural language reasoning when the provided information may be contradictory, and then benchmark various types of language models and show that current models perform poorly on this task.
Abstract: Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated reasoning assumes access to a consistent and coherent set of information over which models reason. When reasoning in the real-world, the available information is frequently inconsistent or contradictory, and therefore models need to be equipped with a strategy to resolve such conflicts when they arise. One widely-applicable way of resolving conflicts is to impose preferences over information sources (e.g., based on source credibility or information recency) and adopt the source with higher preference. In this paper, we formulate the problem of reasoning with contradictory information guided by preferences over sources as the classical problem of defeasible reasoning, and develop a dataset called BoardgameQA for measuring the reasoning capacity of LMs in this setting. BoardgameQA also incorporates reasoning with implicit background knowledge, to better reflect reasoning problems in downstream applications. We benchmark various LMs on BoardgameQA and the results reveal a significant gap in the reasoning capacity of state-of-the-art LMs on this problem, showing that reasoning with conflicting information does not surface out-of-the-box in LMs. While performance can be improved with finetuning, it nevertheless remains poor.
Submission Number: 867
Loading