Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
LLMs often fail to redirect health questions containing misconceptions, unlike clinicians, exposing safety gaps in patient-facing medical AI.
Reasoning models achieve only 2-11% higher accuracy than non-reasoning models when handling queries with false presuppositions, failing to challenge 26-42% of them and remaining sensitive to presupposition strength.
citing papers explorer
-
Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs
Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
-
MedRedFlag: Investigating how LLMs Redirect Misconceptions in Real-World Health Communication
LLMs often fail to redirect health questions containing misconceptions, unlike clinicians, exposing safety gaps in patient-facing medical AI.
-
Evaluating Reasoning Models for Queries with Presuppositions
Reasoning models achieve only 2-11% higher accuracy than non-reasoning models when handling queries with false presuppositions, failing to challenge 26-42% of them and remaining sensitive to presupposition strength.