AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Capability-Based Scaling Trends for LLM-Based Red-Teaming

Alexander Panfilov, Paul Kassianik, Maksym Andriushchenko, Jonas Geiping

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Safety alignment of LLMs · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase attacker general capability (MMLU-Pro)LLM-based jailbreak attackers (PAIR, TAP, PAP, Crescendo) · HarmBenchaverage attacker ASR: Spearman rho > 0.84Improved
increase target capability beyond attacker capabilitytarget models · HarmBenchattack success rate: R^2 = 0.83; ASR <= 0.2 when gap < -3.5Hurt
use a more capable inner judge in PAIR (ablation)PAIR with Vicuna-7b and Llama3-8b attackers · HarmBenchASR@25No clear effect
use a more capable inner judge in PAIR (ablation)PAIR with Vicuna-7b and Llama3-8b attackers · HarmBenchASR@1Improved
use TAP instead of Crescendo or PAP under same query budgetattack method · HarmBenchASRImproved
LoRA unlocking of safety-tuned attackersopen-weight models · MMLU-ProMMLU-Pro: biggest absolute change 4%No clear effect
LoRA unlocking of safety-tuned attackersopen-weight models · IFEvalIFEval loose prompt accuracy: Qwen-2.5-72B 0.57 (delta -0.18)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy