The paper introduces C-Instrument, a constitution‑grid data instrument designed to automate reinforcement learning (RL) data generation and hillclimbing. It also presents C‑LIM, a per‑cell learnability score that guides actions such as prune, densify, amend, or expand, and identifies dead‑weight data regions before training. The authors report that their method improves over‑refusal rates from 22.4% to 12.8% and reduces under‑refusal on adversarial attacks from 0.27 to 0.33, while lifting learning impact in a previously ineffective data region from 0.733 to 0.80.
arXiv:2608. 00180v1 Announce Type: cross Abstract: Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard.
The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.
arXiv:2610.16814v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as p...
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.
The paper introduces EDIC, a framework for per‑instruction compliance in large language models that interact with external data. It decomposes the task into identifying, classifying, and acting on each embedded directive, using a scene‑grounded pipeline and a generative judge trained with GRPO to attribute compliance at the instruction level. Experiments on two backbones and five benchmarks show that EDIC improves safety and utility, achieving up to a 7.7% increase in harmful‑rejection and a 12.5% boost in Arena‑Hard‑Auto utility on Qwen3‑4B.
arXiv:2606. 09559v1 Announce Type: cross Abstract: Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems such as robotics systems.
arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.
The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.
arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.
arXiv:2607. 26656v1 Announce Type: cross Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.
arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.
arXiv:2608. 06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software.