pith. sign in

Harmbench: a standardized evaluation framework for automated red teaming and robust refusal

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Test-Time Safety Alignment

cs.CL · 2026-04-28 · unverdicted · novelty 6.0

Optimizing input embeddings sub-lexically via black-box zeroth-order gradients neutralizes all safety-flagged responses from aligned models on standard benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Test-Time Safety Alignment cs.CL · 2026-04-28 · unverdicted · none · ref 23

    Optimizing input embeddings sub-lexically via black-box zeroth-order gradients neutralizes all safety-flagged responses from aligned models on standard benchmarks.

  • Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control cs.AI · 2026-04-29 · unverdicted · none · ref 59

    LLMs for robotic health attendant control violate safety rules in 54.4% of harmful scenarios on average, with proprietary models at 23.7% median violation versus 72.8% for open-weight models, indicating they are not yet safe for clinical use.