AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025 · 11 citations)
Safety-aligned LLMs can still be jailbroken. Activation steering is a training-free defense that pushes hidden states toward refusal, but it applies one fixed strength to every input. That fixed setting under-protects against some attacks and causes more false refusals of harmless requests. AdaSteer makes the…
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025 · 9 citations)
The paper examines how fine-tuning LLMs for character role-play affects their safety. The authors fine-tuned LLaMA-3-8B-Instruct separately for each of 95 characters from RoleBench. Role-play quality improved, but the models refused harmful AdvBench requests much less often, and villainous characters lost the most…
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent (2026 · 1 citation)
Most emotional support conversation (ESC) systems and benchmarks only measure empathetic wording in text-only settings.

Co-authors here

10 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 20 times (of the 149,439 papers whose bibliographies we read); 6 citing papers with a page here →.

Updated 31 October 2026