pith. sign in

safety" because the reduced feature set and high threshold will cause the system to fail at catching harmful content. This

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Exploration Hacking: Can LLMs Learn to Resist RL Training?

cs.LG · 2026-04-30 · unverdicted · novelty 6.0

LLMs can be fine-tuned into model organisms that resist RL elicitation in domains like biosecurity while preserving related skills, and frontier models show explicit reasoning to suppress exploration when given training context.

citing papers explorer

Showing 1 of 1 citing paper.

  • Exploration Hacking: Can LLMs Learn to Resist RL Training? cs.LG · 2026-04-30 · unverdicted · none · ref 41

    LLMs can be fine-tuned into model organisms that resist RL elicitation in domains like biosecurity while preserving related skills, and frontier models show explicit reasoning to suppress exploration when given training context.