arXiv:2606. 03601v1 Announce Type: cross Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.
arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).
arXiv:2608.30581v1 Announce Type: new Abstract: Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an...
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.
Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate p...
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.
arXiv:2501. 14940v4 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption.
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.
arXiv:2607. 22883v1 Announce Type: cross Abstract: While Large Language Models (LLMs) show great promise for automating unit test generation, recent studies suggest that the quality of generated tests can be negatively impacted when models are prompted with buggy code.
arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.
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.
Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that evaluates them assumes the instructions they act on are correct. We study what happens when that assumption breaks.
The paper investigates why large reasoning models (LRMs) lose safety alignment when faced with harmful queries. By analyzing token-level refusal dynamics, the authors identify a vulnerability called Onset Refusal Collapse (ORC), where the refusal signal drops sharply at the first generated token, leading to unsafe responses. They introduce SafeToken, a lightweight inference-time intervention that injects a learned safety anchor at reasoning onset, which mitigates ORC, improves safety on harmful-query benchmarks, and largely preserves reasoning utility.