pith. sign in

Does refusal training in llms generalize to the past tense?

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

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1 cs.CR 1

years

2026 1 2025 1

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

LLM-Agnostic Semantic Representation Attack

cs.CL · 2026-05-09 · unverdicted · novelty 6.0

SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.

LLM-Safety Evaluations Lack Robustness

cs.CR · 2025-03-04 · unverdicted · novelty 4.0

LLM safety evaluations are hindered by noise in dataset curation, automated red-teaming, response generation, and LLM-judge evaluation, making fair comparisons difficult and slowing progress.

citing papers explorer

Showing 2 of 2 citing papers.

  • LLM-Agnostic Semantic Representation Attack cs.CL · 2026-05-09 · unverdicted · none · ref 27

    SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.

  • LLM-Safety Evaluations Lack Robustness cs.CR · 2025-03-04 · unverdicted · none · ref 5

    LLM safety evaluations are hindered by noise in dataset curation, automated red-teaming, response generation, and LLM-judge evaluation, making fair comparisons difficult and slowing progress.