arXiv:2606. 09388v1 Announce Type: new Abstract: Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment.
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
arXiv:2602. 16835v2 Announce Type: replace-cross Abstract: Safety alignment is essential for the responsible deployment of Large Language Models (LLMs).
CLEAR is a conditional safety adaptation framework that employs a lightweight hidden‑state gate to continuously control the activation strength of a safety low‑rank adapter. It aims to reduce harmful completions while preserving the performance of the frozen backbone on benign prompts. Experiments on safety and utility benchmarks, including HarmBench and GSM8K, show that CLEAR significantly lowers HarmBench ASR and improves utility compared to globally applied safety tuning methods such as SFT or standard LoRA.
The paper introduces a modular correction framework for large language models that uses Activated LoRA adapters and a context-aware routing mechanism to mitigate harmful outputs. By allowing expert adapters to activate mid-sequence without invalidating the KV cache, the system achieves low-latency, targeted correction during generation. Experiments show improved alignment on safety benchmarks while maintaining task performance, presenting a lightweight, scalable approach to safer LLM deployments.
The paper examines the safety of small language models (SLMs) deployed on resource‑constrained, on‑device platforms, focusing on the LLaMA‑2‑7B‑Chat model. It shows that safety‑sensitive behavior is concentrated in a sparse subset of parameters, particularly the MLP down_proj layer, and that altering only 0.19% of these weights can significantly affect safety metrics while leaving overall accuracy largely unchanged. The study suggests that targeted fault analysis and selective integrity protection could improve safety for on‑device, agentic language models.
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.
arXiv:2606. 05290v1 Announce Type: cross Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture.
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
arXiv:2606. 16808v1 Announce Type: new Abstract: While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries.
arXiv:2506. 08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures.
arXiv:2606. 06519v1 Announce Type: new Abstract: Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful.
arXiv:2508.15526v2 Announce Type: replace Abstract: The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabili...