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

• URL: http://arxiv.org/abs/2605.24154v1
• Date: Fri, 22 May 2026 19:22:17 GMT
• Title: Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
• Abstract summary: Current safety alignment of foundation models largely follows a emphone-size-fits-all paradigm.<n>We propose textscPalette, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains.<n>Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation.
• Score: 39.416807881947875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 general users but legitimate for authorized professionals, limiting helpfulness in specialized professional settings. Existing approaches either require costly realignment or rely on inference-time steering that suffers from imprecise control and added latency. To this end, we propose \textsc{Palette}, a modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere. Our method identifies a refusal direction via multi-objective search and internalizes it into the model through lightweight adaptation. \textsc{Palette} further supports modular composition: it learns domain-specific safety controls independently and composes them through parameter merging, enabling on-demand multi-domain authorization without retraining. Experiments across four safety benchmarks, multiple model variants, and both LLMs and VLMs show that \textsc{Palette} delivers precise safety control without sacrificing general utility, offering a practical path toward foundation models that adapt to diverse professional needs.

Related papers

• An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS [3.37470725921294]
  Large Language Models (LLMs) are powerful zero-shot learners but remain prone to misalignment with human preferences.<n>We propose a modular correction framework that augments pretrained LLMs with Activated LoRA adapters and a context-aware routing mechanism.
  arXiv  Detail & Related papers  (2026-09-12T00:24:49Z)
• Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Family Representation Steering [9.4417382684481]
  Inference-time methods fail to reliably improve safety without disrupting domain capability.<n>We propose CREST, an inference-time alignment method that steers base model hidden representations using safety directions extracted from a guidance model of any family.<n>CREST improves safety where specialization has weakened it while preserving both domain-specific capability and the safety of already well-aligned models.
  arXiv  Detail & Related papers  (2026-08-31T06:34:58Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse [0.0]
  We present a neuro-symbolic multi-agent system that re-conceptualizes requirements reuse as a Model-Driven Elicitation process.<n>Our system achieves 100% requirement coverage and a constraint-violation rate of only 0.2%.
  arXiv  Detail & Related papers  (2026-05-02T18:16:04Z)
• MOSAIC: Composable Safety Alignment with Modular Control Tokens [22.486612919976977]
  Real-world deployments often require context-dependent safety rules that vary across users, regions, and applications.<n>We propose MOSAIC, a modular framework that enables compositional safety alignment through learnable control tokens optimized over a frozen backbone model.<n>Experiments show that MOSAIC achieves strong defense performance with substantially lower over-refusal while preserving model utility.
  arXiv  Detail & Related papers  (2026-03-17T07:40:43Z)
• Feasibility Restoration under Conflicting STL Specifications with Pareto-Optimal Refinement [18.383508411056944]
  Signal Temporal Logic (STL) is expressive language that specifies expressive requirements in robotics.<n>STL specifications may become conflicting in real-world applications, where safety rules, traffic regulations, task and objectives can be cannot be satisfied together.<n>We propose a unified two-stage framework that first restores feasibility via minimal relaxation, then refine the feasible solution by formulating it as a value-aware multi-objective optimization problem.
  arXiv  Detail & Related papers  (2026-03-06T23:41:01Z)
• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements [46.79887158348167]
  The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach.<n>We propose Controllable Safety Alignment (CoSA), a framework designed to adapt models to diverse safety requirements without re-training.
  arXiv  Detail & Related papers  (2024-10-11T16:38:01Z)

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.