Pith. sign in

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 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Robust Critics: Defending LLMs Against Multi-Turn Attacks

cs.AI · 2026-05-24 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Robust Critics: Defending LLMs Against Multi-Turn Attacks cs.AI · 2026-05-24 · conditional · none · ref 34

    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.