Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables adaptive safety regulation without model retraining or parameter modification. The method formulates dialogue generation as a sequential decision process, where a reinforcement learning agent dynamically selects prompt adjustment strategies based on contextual feedback. This allows unsafe behaviours to be suppressed through iterative refinement, which we conceptualise as inference-time behavioural unlearning. Evaluated across multiple LLMs and unsafe dialogue scenarios, SafeCtrl-RL consistently improves safety and response quality, outperforms existing prompt-based optimisation methods, and achieves favourable performance--efficiency trade-offs. **Warning: This paper may contain examples of harmful language, and reader discretion is recommended.
Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest that robust safety requires context-invariant alignment, where behavior depends on the underlying intent rather than surface form. Enforcing invariance is difficult in alignment because not all training signals are equally trustworthy; for some prompt variants we can obtain verifiable feedback (e.g., multiple-choice), while for open-ended variants we typically rely on noisy, gameable reward proxies (e.g., learned judges). As a result, standard symmetric invariance regularizers can reduce cross-context discrepancies by lowering performance on reliable variants instead of improving open-ended robustness. To address this, we introduce Anchor Invariance Regularization (AIR), which treats verifiable prompts as anchors and uses a stop-gradient target to regularize only the open-ended variants toward the anchor performance. AIR is implemented as a plug-in auxiliary loss and combined with group-based preference optimization (e.g., GRPO) via heterogeneous prompt grouping. Across Safety, Moral Reasoning, and Math, AIR improves context invariance, boosting in-distribution group accuracy by 12.71% and out-of-distribution consistency by 33.49%, making safety constraints robust to adversarial framings.
Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones. However, we show that the same request can elicit substantially different safety decisions under different traits assigned in the system prompt, a failure mode we call trait-induced safety variation. To measure this failure, we introduce refusal-based metrics: Trait-Induced Deviation measures dataset-level deviation from the no-trait baseline, while Trait-Induced Flip Rate measures whether the same request receives different safety decisions across traits. We then provide a representation-level analysis of the mechanism behind trait-induced safety shifts and find that traits perturb the model's safety representations within a low-dimensional subspace. To achieve trait-invariant safety, where safety behavior remains stable across traits, we introduce Trait-Invariant Safety Tuning (TIST), a simple yet effective self-distillation framework that aligns an LLM's trait-conditioned behavior with its no-trait behavior. Guided by our analysis, we further propose Trait-Subspace Neutralization (TraSN), an instantiation of TIST, which enforces invariance only within the identified trait subspace. Experiments show that TraSN improves trait-invariant safety and strengthens harmful-request safety while preserving general capability. Our results highlight traits as an important factor in LLM safety and robust model behavior.
Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing methods often fail to be simultaneously effective, utility-preserving, and training-efficient due to their rigid, one-size-fits-all designs and limited adaptability. In this work, we present FineSteer, a novel steering framework that decomposes inference-time steering into two complementary stages: conditional steering and fine-grained vector synthesis, allowing fine-grained control over when and how to steer internal representations. In the first stage, we introduce a Subspace-guided Conditional Steering (SCS) mechanism that preserves model utility by avoiding unnecessary steering. In the second stage, we propose a Mixture-of-Steering-Experts (MoSE) mechanism that captures the multimodal nature of desired steering behaviors and generates query-specific steering vectors for improved effectiveness. Through tailored designs in both SCS and MoSE, FineSteer maintains robust performance on general queries while adaptively optimizing steering vectors for targeted inputs in a training-efficient manner. Extensive experiments on safety and truthfulness benchmarks show that FineSteer outperforms state-of-the-art methods in overall performance, achieving stronger steering performance with minimal utility loss. Code is available at https://github.com/YukinoAsuna/FineSteer