MDCR: A Dataset for Multi-Document Conditional Reasoning

TL;DR

This paper introduces MDCR, a new dataset designed to evaluate models' ability to perform complex multi-document conditional reasoning and optimization, reflecting real-world decision-making challenges.

Contribution

The paper presents MDCR, a novel dataset for multi-document conditional reasoning and optimization, addressing limitations of previous single-document datasets and enabling advanced model evaluation.

Findings

Current LLMs show limitations in solving multi-document conditional reasoning tasks.

MDCR reflects real-world complexity and challenges for AI models.

The dataset facilitates future research in optimization and reasoning with unknown conditions.

Abstract

The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models' capability of reading a document and answering eligibility questions, considering unmentioned conditions. However, it is limited to questions on single documents, neglecting harder cases that may require cross-document reasoning and optimization, for example, "What is the maximum number of scholarships attainable?" Such questions over multiple documents are not only more challenging due to more context having to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models' capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.