Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence

• URL: http://arxiv.org/abs/2604.08169v1
• Date: Thu, 09 Apr 2026 12:28:22 GMT
• Title: Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
• Abstract summary: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization.<n>Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via steering.<n>These findings motivate activation steering as a lightweight runtime defense that continuously corrects misaligned activations throughout generation.
• Score: 16.403654360036498
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via steering, while safety alignment has been shown to govern the first few output tokens primarily, leaving subsequent generation unguarded. These findings motivate activation steering as a lightweight runtime defense that continuously corrects misaligned activations throughout generation. We evaluate three methods: Steer-With-Fixed-Coeff (SwFC), which applies uniform additive steering, and two novel projection-aware methods, Steer-to-Target-Projection (StTP) and Steer-to-Mirror-Projection (StMP), that use a logistic regression decision boundary to selectively intervene only on tokens whose activations fall below distributional thresholds. Using malicious system prompts as a controlled proxy for misalignment, we evaluate under two threat models (dishonesty and dismissiveness) and two architectures (Llama-3.3-70B-Instruct, Qwen3-32B). All methods substantially recover target traits (honesty and compassion) while preserving coherence. StTP and StMP better maintain general capabilities (MMLU, MT-Bench, AlpacaEval) and produce less repetition in multi-turn conversations.

Related papers

• Robust Activation Map Rectification for Weakly Supervised Volumetric Segmentation: Temporal Coherence as a Free Lunch [31.156115062163412]
  Weakly supervised segmentation relies heavily on class activation maps (CAMs) to initially localize target regions.<n>Existing remedies typically introduce additional training stages or prototype learning, increasing computational cost and reducing robustness.<n>We propose a training-free prototype-free framework that rectifies unreliable CAMs by exploiting temporal and structural coherence in volumetric data as a free lunch.
  arXiv  Detail & Related papers  (2026-07-22T08:07:38Z)
• The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs [1.4323566945483497]
  We introduce Contrastive Logit Steering ( CLS), a zero-optimization framework that isolates the "refusal direction"<n> CLS operates directly on the output distribution, serving as a diagnostic probe for alignment.<n>Our experiments on 7 model families reveal that safety implementation is architecturally deterministic.
  arXiv  Detail & Related papers  (2026-06-21T22:04:48Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)
• Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection [1.7802147489386628]
  Large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors.<n>We propose Selective Steering, which addresses these limitations through two key innovations.<n> Experiments across nine models demonstrate that Selective Steering achieves 5.5x higher attack success rates than prior methods.
  arXiv  Detail & Related papers  (2026-01-27T08:56:25Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong [19.134202394422285]
  Adaptive Multi-Branch Steering (AMBS) is a two-stage 1-to-N framework for unified and efficient multi-objective alignment.<n>AMBS consistently improves HHH alignment across multiple 7B LLM backbones.
  arXiv  Detail & Related papers  (2025-09-26T15:52:21Z)
• TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs [7.125400292079228]
  Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift.<n>While prior work has behaviorally characterized alignment failure, little is known about the training-time belief sources underlying these failures.<n>We introduce TraceAlign, a unified framework for tracing unsafe completions back to their root causes in the model's training corpus.
  arXiv  Detail & Related papers  (2025-08-04T05:03:35Z)
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
  Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
  arXiv  Detail & Related papers  (2025-05-15T17:58:33Z)
• AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender [99.3105257001476]
  We propose AdaSteer, an adaptive activation steering method that adjusts model behavior based on input characteristics.<n>AdaSteer steers input representations along both the Rejection Direction (RD) and Harmfulness Direction (HD)<n>Our results highlight the potential of interpretable model internals for real-time, flexible safety enforcement in LLMs.
  arXiv  Detail & Related papers  (2025-04-13T07:39:17Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [81.98466438000086]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Making Large Language Models Better Reasoners with Alignment [57.82176656663245]
  Reasoning is a cognitive process of using evidence to reach a sound conclusion. Recent studies reveal that fine-tuning LLMs on data with the chain of thought (COT) reasoning process can significantly enhance their reasoning capabilities. We introduce an textitAlignment Fine-Tuning (AFT) paradigm, which involves three steps.
  arXiv  Detail & Related papers  (2023-09-05T11:32:48Z)

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.