Critic-weighted sampling over inferred user intents improves multi-turn LLM defense success while preserving helpfulness, with an expected-Q improvement guarantee and transfer to frontier models.
Discern truth from falsehood: Reducing over-refusal via contrastive refinement.CoRR, abs/2603.03323, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Robust Critics: Defending LLMs Against Multi-Turn Attacks
Critic-weighted sampling over inferred user intents improves multi-turn LLM defense success while preserving helpfulness, with an expected-Q improvement guarantee and transfer to frontier models.