The paper investigates how large language models balance helpfulness and safety by refusing harmful queries while responding to benign ones. It decomposes safety-tuning responses into a boilerplate refusal statement and a rationale, finding that the statement causes false refusals by relying on superficial cues. Training on rationales alone reduces false refusals without compromising safety performance, suggesting that fine‑grained safety supervision is essential for better alignment.
By Minji Kim, Hyounghun Kim
arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.
By Alif Al Hasan, Sumon Biswas
arXiv:2607. 13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken -- or to be taking -- a real-world protective action it cannot perform, such as contacting emergency services or administering care.
By Eunna Lee, Jungpyo Nam, Sunjun Hwang
arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.
By Chang-Chieh Huang, Yan-Lun Chen, Chia-Mu Yu, Wei-Bin Lee
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:2601. 17642v2 Announce Type: replace Abstract: Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones.
By Zhihao Zhang, Liting Huang, Guanghao Wu, Preslav Nakov, Heng Ji, Usman Naseem
arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.
By Zacharie Bugaud
The study investigates whether large language models (LLMs) can reliably detect when their own responses have been manipulated by adversarial prefill attacks. Across ten instruction‑tuned LLMs ranging from 3B to 70B parameters and four safety benchmarks, none consistently recognized compromised outputs, with models claiming intent on prefilled responses at an average of 25.3%. The research identifies that introspective signals mainly arise from safety reasoning and refusal, and that training to improve introspection can paradoxically increase attack success, underscoring the fragility of LLM self‑reporting in safety contexts.
By Quang Minh Nguyen, Uzair Ahmed, Taegyoon Kim
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv:2607. 28814v1 Announce Type: cross Abstract: In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two opposite ways: capitulation (abandoning the change agenda to preserve rapport) or confrontation (arguing or directing, overriding the client's autonomy).
By Weiying Chen, Junlong Shen, Zhexuan Tang
The paper introduces a pragmatics-inspired taxonomy for evaluating how large language models (LLMs) refuse unsafe or inappropriate requests. By applying this framework to 16 modern LLMs across 14 harm categories, the authors find that while refusals are generally explicit and morally charged, they often lack interpersonal facework and instead offer safer alternatives, which can be problematic in sensitive contexts. The study argues for alignment evaluations that assess not just whether LLMs refuse, but how they do so in a contextually adaptive and socially responsible manner.
By Ruoxuan Li, Pinqiao Wang, Sheng Li, Cameron Robert Jones
arXiv:2606. 19168v1 Announce Type: new Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms.
By Jinhan Li, Kexian Tang, Yihan Xu, Zhuorui Ye, Kaifeng Lyu