The paper addresses the problem of over‑refusal in safety‑aligned large language models, where benign instructions are incorrectly rejected. It identifies that a small set of hypersensitive safety heads in transformer attention misfire on hard‑safe prompts, causing abnormal attention entanglement and high‑entropy routing conflicts that block necessary attention to target entities. To mitigate this, the authors propose Semantic Routing Calibration (SRC), a lightweight, training‑free inference framework that dynamically suppresses these hypersensitive heads and fuses logits from dual branches to restore trustworthy reasoning while preserving intrinsic safety performance.
By Zixuan Wang, Bingjie Zhang, He Zhao, Dandan Guo
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
By Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre C\^ot\'e, Sarath Chandar
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
By Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei
The paper introduces RASET, a router‑agnostic safety‑critical expert tuning framework for Mixture‑of‑Experts (MoE) large language models. RASET identifies a small subset of experts that are responsible for safety enforcement and applies parameter‑efficient tuning only to those experts, preserving the model’s intrinsic routing behavior. Experiments on five open‑weight MoE backbones show that RASET achieves a high safety‑bypass yield, outperforming existing baselines by a significant margin.
By Zhibo Zhang, Yuxi Li, Zhen Ouyang, Ling Shi, Kailong Wang
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
arXiv:2609.00051v1 Announce Type: cross
Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...
By Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
By Joshua Adrian Cahyono
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
By Jason Vega, Gagandeep Singh
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang
The paper investigates why large language models lose safety alignment after benign fine‑tuning. It argues that safety alignment relies on a low‑rank, output‑routing geometry that becomes flatter during fine‑tuning, and that after only 100 benign examples this routing is sharpened in output‑side MLPs, leading to fragile safety while general performance remains relatively intact. Techniques like LoRA and ASAM can delay this collapse by reducing output‑side sharpness, but their effectiveness diminishes with larger fine‑tuning scales.
By Yitong Guo, Xiaoyi Chen, Siyuan Zhang, Xiaofeng Wang, Haixu Tang