paper-with-me

Papers

Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements

2024-10-11 · Jingyu Zhang, Ahmed Elgohary, Ahmed Magooda, Daniel Khashabi, Benjamin Van Durme

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face of varying social norms across cultures and regions. In addition, users may have diverse safety needs, making a model with static safety standards too restrictive to be useful, as well as too costly to be re-aligned. We propose Controllable Safety Alignment (CoSA), a framework designed to adapt models to diverse safety requirements without re-training. Instead of aligning a fixed model, we align models to follow safety configs -- free-form natural language descriptions of the desired safety behaviors -- that are provided as part of the system prompt. To adjust model safety behavior, authorized users only need to modify such safety configs at inference time. To enable that, we propose CoSAlign, a data-centric method for aligning LLMs to easily adapt to diverse safety configs. Furthermore, we devise a novel controllability evaluation protocol that considers both helpfulness and configured safety, summarizing them into CoSA-Score, and construct CoSApien, a human-authored benchmark that consists of real-world LLM use cases with diverse safety requirements and corresponding evaluation prompts. We show that CoSAlign leads to substantial gains of controllability over strong baselines including in-context alignment. Our framework encourages better representation and adaptation to pluralistic human values in LLMs, and thereby increasing their practicality.

📄 PDF Abstract BibTeX arXiv:2410.08968

Code (0)

등록된 구현이 없습니다.

Tasks

Safety Alignment

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs

2026-05-22 · Qitao Tan, Xiaoying Song, Arman Akbari, Arash Akbari 외 arxiv

Current safety alignment of foundation models largely follows a \emph{one-size-fits-all} paradigm, applying the same refusal policy across users and contexts. As a result, models may refuse requests that are unsafe for g…

UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models

2025-10-02 · Yuhao Sun, Zhuoer Xu, Shiwen Cui, Kun Yang 외 arxiv

Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks. Existing safety techniques -- i…

Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning

2026-04-29 · Seungyub Han, Hyungjin Kim, Jungwoo Lee arxiv

Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavior. To address this, we present SAS (Self-Alignment for Safety), a tra…

Reinforcement LearningTest-time AdaptationBayesian Inference

Parameter-Efficient Tuning Helps Language Model Alignment

2023-10-01 · Tianci Xue, Ziqi Wang, Heng Ji

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback f…

Language ModelingLanguage Modellingmodel

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs

2025-06-21 · Shuang Ao, Yi Dong, Jinwei Hu, Sarvapali Ramchurn

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing s…

Safety Alignment