Evaluating Reasoning Models for Queries with Presuppositions

TL;DR

This paper evaluates large reasoning models' ability to handle queries with presuppositions, revealing modest improvements over non-reasoning models but persistent challenges with false assumptions.

Contribution

It introduces a benchmark for assessing reasoning models on presupposition queries and provides insights into their strengths and limitations in challenging false assumptions.

Findings

Reasoning models achieve 2-11% higher accuracy than non-reasoning models.

Models fail to challenge 26-42% of false presuppositions.

Model susceptibility depends on presupposition strength.

Abstract

Millions of users turn to AI models for their information needs. It is conceivable that a large number of user queries contain assumptions that may be factually inaccurate. Prior work notes that large language models (LLMs) often fail to challenge such erroneous assumptions, and can reinforce users' misinformed opinions. However, given the recent advances, especially in model's reasoning capabilities, we revisit whether large reasoning models (LRMs) can reason about the underlying assumptions and respond to user queries appropriately. We construct queries with varying degrees of presuppositions spanning health, science, and general knowledge, and use it to evaluate several widely-deployed models When compared to non-reasoning models, we find that reasoning models achieve a slightly higher accuracy (2-11%), but they still fail to challenge a large fraction (26-42%) of false presuppositions. Further, reasoning models remain susceptible to how strongly the presupposition is expressed.