paper-with-me

홈 › Papers

Evaluating Reasoning Models for Queries with Presuppositions

2026-05-04 · Rose Sathyanathan, Kinshuk Vasisht, Danish Pruthi arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.03050

Code (0)

등록된 구현이 없습니다.

Tasks

General Knowledge

Similar Papers 제목 키워드 기반

Evaluating Large Language Models for Health-related Queries with Presuppositions

2023-12-14 · Navreet Kaur, Monojit Choudhury, Danish Pruthi

As corporations rush to integrate large language models (LLMs) to their search offerings, it is critical that they provide factually accurate information that is robust to any presuppositions that a user may express. In …

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models

2023-10-10 · CVPR 2024 1 · Letian Zhang, Xiaotong Zhai, Zhongkai Zhao, Yongshuo Zong 외

Counterfactual reasoning, a fundamental aspect of human cognition, involves contemplating alternatives to established facts or past events, significantly enhancing our abilities in planning and decision-making. In light …

BenchmarkingCode GenerationcounterfactualCounterfactual Reasoning+2

NOPE: A Corpus of Naturally-Occurring Presuppositions in English

2021-09-14 · CoNLL (EMNLP) 2021 11 · Alicia Parrish, Sebastian Schuster, Alex Warstadt, Omar Agha 외

Understanding language requires grasping not only the overtly stated content, but also making inferences about things that were left unsaid. These inferences include presuppositions, a phenomenon by which a listener lear…

Cancer-Myth: Evaluating AI Chatbot on Patient Questions with False Presuppositions

2025-04-15 · Wang Bill Zhu, Tianqi Chen, Ching Ying Lin, Jade Law 외

Cancer patients are increasingly turning to large language models (LLMs) as a new form of internet search for medical information, making it critical to assess how well these models handle complex, personalized questions…

Chatbot

Finite State Reasoning for Presupposition Satisfaction

2018-08-01 · COLING 2018 8 · Jacob Collard

Sentences with presuppositions are often treated as uninterpretable or unvalued (neither true nor false) if their presuppositions are not satisfied. However, there is an open question as to how this satisfaction is calcu…

Open-Ended Question Answering