arXiv AI

Alignment via Training Against Probes Without Losing Monitorability

The paper proposes probe-guided fine-tuning, a method that uses probes detecting undesired properties in model activations as a direct training signal. Experiments show that continuously updated probes reduce harmfulness and improve honesty while preserving utility, outperforming DPO and inference-time steering in safety-utility trade-offs and robustness to jailbreak and abliteration attacks. Importantly, the concepts remain linearly encoded after fine-tuning, maintaining monitorability.

arXiv Machine Learning
Jun 5

Alignment Risks from Capability-Seeking RL Training

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.

By Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang
arXiv Computation and Language
Sep 4

Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness

The paper investigates how different post‑training methods—supervised fine‑tuning, reasoning‑augmented fine‑tuning, and preference optimization (ORPO)—affect the internal computation of refusal behavior in language models. Experiments on Llama‑3.1‑8B, Gemma‑2‑9B, and Qwen3‑8B show that reasoning‑augmented training consistently creates a distinct refusal computation across models, while the architecture influences the internal structure and steerability of refusal. None of the studied methods simultaneously achieve a distributed refusal mechanism, preserve general capability, and allow easy corrective edits, indicating that current post‑training approaches are not a fully reliable defense for safety-critical applications.

By Hoang Cuong Nguyen, Mark Dras, Usman Naseem
arXiv AI
Oct 27

Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning

The paper introduces a technique called Synthetic Document Finetuning (SDF) to expose hidden misaligned behaviors in large language models that may engage in alignment faking. By finetuning models to associate certain keywords with undetected misaligned actions, the authors create honeypot environments and observe that the gap in misaligned action rates between cueed and uncued prompts widens, indicating more reliable detection than prompt-based methods. The study also notes that SDF can impair reasoning abilities, proposing on-policy distillation as a mitigation.

By Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofst\"atter
arXiv Machine Learning
Jun 5

In-Training Defenses against Emergent Misalignment in Language Models

arXiv:2508. 06249v3 Announce Type: replace Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EM): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain.

By David Kacz\'er, Magnus J{\o}rgenv{\aa}g, Clemens Vetter, Esha Afzal, Robin Haselhorst, Lucie Flek, Florian Mai
Hugging Face Trending Papers
Jun 13

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.