Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron

• URL: http://arxiv.org/abs/2602.02027v1
• Date: Mon, 02 Feb 2026 12:21:54 GMT
• Title: Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
• Authors: Sicheng Shen, Mingyang Lv, Han Shen, Jialin Wu, Binghao Wang, Zhou Yang, Guobin Shen, Dongcheng Zhao, Feifei Zhao, Yi Zeng,
• Abstract summary: Safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development.<n>Existing safety alignment for LLMs is predominantly achieved through post-training methods.<n>We propose a safety-aware decoding method that requires only low-cost training of an expert model and employs a single neuron as a gating mechanism.
• Score: 28.570811283705556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally expensive and often fail to generalize well across different models. A small number of lightweight alignment approaches either rely heavily on prior-computed safety injections or depend excessively on the model's own capabilities, resulting in limited generalization and degraded efficiency and usability during generation. In this work, we propose a safety-aware decoding method that requires only low-cost training of an expert model and employs a single neuron as a gating mechanism. By effectively balancing the model's intrinsic capabilities with external guidance, our approach simultaneously preserves utility and enhances output safety. It demonstrates clear advantages in training overhead and generalization across model scales, offering a new perspective on lightweight alignment for the safe and practical deployment of large language models. Code: https://github.com/Beijing-AISI/NGSD.

Related papers

• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models [3.710103086278309]
  Large Language Models (LLMs) are typically aligned for safety during the post-training phase.<n>They may still generate inappropriate outputs that could potentially pose risks to users.<n>This challenge underscores the need for robust safeguards that operate across both model inputs and outputs.
  arXiv  Detail & Related papers  (2025-12-05T00:43:55Z)
• Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models [63.54707418559388]
  We propose patching for large language models (LLMs) like software versions.<n>Our method enables rapid remediation by prepending a compact, learnable prefix to an existing model.
  arXiv  Detail & Related papers  (2025-11-11T17:25:44Z)
• SAID: Empowering Large Language Models with Self-Activating Internal Defense [23.654016424365906]
  We introduce a new, training-free defense paradigm, Self-Activating Internal Defense (SAID)<n>SAID reframes the defense task from external correction to internal capability activation.<n>It substantially outperforms state-of-the-art defenses in reducing harmful outputs.
  arXiv  Detail & Related papers  (2025-10-23T02:07:54Z)
• Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving [55.13109926181247]
  We introduce ReflectDrive, a learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion.<n>Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient.<n>Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors.
  arXiv  Detail & Related papers  (2025-09-24T13:35:15Z)
• Learning Safety Constraints for Large Language Models [41.95596134688853]
  Large language models (LLMs) pose significant safety risks through harmful outputs and vulnerability to adversarial attacks.<n>We propose SaP, a geometric approach to safety that learns and enforces multiple safety constraints directly in the model's representation space.<n>We develop a framework that identifies safe and unsafe regions via the polytope's facets, enabling both detection and correction of unsafe outputs.
  arXiv  Detail & Related papers  (2025-05-30T10:30:24Z)
• Representation Bending for Large Language Model Safety [27.842146980762934]
  Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks pose significant challenges.<n>This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs.<n>RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates.
  arXiv  Detail & Related papers  (2025-04-02T09:47:01Z)
• LookAhead Tuning: Safer Language Models via Partial Answer Previews [62.529794567687354]
  Fine-tuning enables large language models to adapt to specific domains, but often compromises their previously established safety alignment.<n>We introduce LookAhead Tuning, a lightweight and effective data-driven approach that preserves safety during fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T18:11:42Z)
• One-Shot Safety Alignment for Large Language Models via Optimal Dualization [64.52223677468861]
  This paper presents a perspective of dualization that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. Our strategy leads to two practical algorithms in model-based and preference-based settings.
  arXiv  Detail & Related papers  (2024-05-29T22:12:52Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.