arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
arXiv:2606. 04160v1 Announce Type: cross Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests.
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.
The paper investigates how refusal training shapes the internal geometry of language models, showing that activation updates from refusal-completion losses create a distinct low‑dimensional refusal subspace. In a case study on OLMo‑2‑0425‑1B‑Instruct, the authors link the brittleness of refusal directions to repetitive refusal prefixes and demonstrate that using diverse refusal starts can increase the stable rank of gradients, thereby hardening the model against vector‑ablation attacks. The work provides insights into the emergence of safety‑critical features and offers a potential strategy to strengthen refusal robustness.
arXiv:2606.22676v2 Announce Type: replace Abstract: Refusal on a safety benchmark does not reveal how stable that behavior will remain after model updates. Benign downstream fine-tuning can weaken re...
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:2608.29109v1 Announce Type: new Abstract: Large language models often answer structurally unanswerable questions, such as computing cot(-540{\deg}) or evaluating (1).startswith("1"), instead of...
arXiv:2608.30197v1 Announce Type: new Abstract: Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on beni...
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
arXiv:2608. 03201v1 Announce Type: new Abstract: Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs.
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.