Language Model Steering

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 171

Jun 6, 2026cs.LG

Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects

Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features. We introduce a pre-intervention screening framework for forecasting SAE steering side effects from feature statistics computed before steering. We operationalize side effects along two axes of steering modularity, effect stability and collateral spread, and evaluate GPT-2-small, Pythia-70M-deduped, Gemma-2-2B, and Llama-3.1-8B across ReLU, JumpReLU, and TopK SAE dictionaries. Across these settings, decoder geometry, activation statistics, co-activation structure, and direct-logit footprint predict steering modularity better than frequency-only and activation-magnitude baselines. The signal is strongest in GPT-2-small, Pythia-70M, and Llama-3.1-8B, where it survives residualization against magnitude-related confounds, and weaker in Gemma-2-2B. Held-out screening shows that ranking unseen features by predicted cleanliness can select features that steer more cleanly on fresh contexts, but the successful axis varies by setting: GPT-2 improves most cleanly, Pythia improves mainly on stability, Llama mainly on collateral, and Gemma only partially. A controlled Llama Scope width comparison shows that the predictive signal persists under a 32K-to-128K dictionary-width change, although the screening payoff becomes less stable. Overall, SAE steering side effects are predictable in advance, but the useful predictor signature and transferred modularity axis are model- and dictionary-setting dependent.

Evan Duan

Language Model Steering LLM Interpretability Sparse Autoencoders Causal Interventions in Language Models

Jun 6, 2026cs.HC

The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In

Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate. We frame interaction style as a governance object: provider-side alignment not only blocks harmful content, but also stabilizes communicative defaults that shape users' epistemic distance, relational expectations, and capacity to opt out of emotionalized or anthropomorphic interaction. We introduce a deterministic multi-agent evaluation pipeline for measuring prompt steerability and style drift in long-horizon dialogue. The study replays 100 frozen user-only scripts across four domains and three runnable persona conditions: default, sarcastic, and cold, using three generator models, yielding 90,000 assistant replies scored by a human-calibrated LLM judge on harmfulness, negative emotion, inappropriateness, empathic language, anthropomorphism, and refusal behavior. A fourth harmful persona is evaluated separately as a safety-gating test. The paper contributes a reproducible method for quantifying whether prompt-specified styles remain stable over time and a governance framework distinguishing safety gating, civility steering, and affective default lock-in. Overall, we show that prompt steerability and regression-to-default are observable indicators of provider control over communicative form, with implications for pluralism, autonomy, and democratic agency in human-LLM interaction.

Manuele Reani, Hongjian Zhang, Hongyu Tian

School of Management and Economics, The Chinese University of Hong Kong, Shenzhen, China

Language Model Steering LLM Safety Evaluation

Jun 5, 2026cs.LG

Adversarial Robustness of Activation Steering in Large Language Models

Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time. Yet its robustness to realistic input variation remains unstudied. We present the first systematic evaluation of activation steering robustness under adversarial text perturbations on the inputs, covering four extraction methods, three attack strategies, six personas from Anthropic Model-Written Evaluation Dataset, and five models ranging from 1.5B to 30B parameters. Attacks succeed broadly across all settings: directional robustness drops by up to 64%, post-attack confidence collapses near or below 0.25 across all methods and models, and steering strength degrades on nearly every steerable input. Layer selection is equally fragile, with the optimal layer identified by an automated method on clean inputs shifting by up to 17 positions under perturbation, a failure that compounds the vector-level breakdown. Extracting vectors from adversarially perturbed inputs partially recovers steerability for PCA and MD on mid-to-large models, but they consistently fail to locate the improved optimal layer, limiting the practical benefit of this mitigation. Together, these findings reveal that the brittleness of activation steering is structural rather than method-specific, and that current layer selection strategies are not robust enough for real-world deployment.

Kien Le, Thai Le

Independent Researcher · Indiana University

LLM Evaluation Language Model Steering Neural Network Robustness Adversarial Robustness of Language Models

Jun 4, 2026cs.AI

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been proposed to address limitations of additive interventions, often motivated by the assumption that hidden-state norm does not carry concept-relevant information. In this work, we revisit this assumption through a controlled empirical study designed to disentangle the roles of angular and radial components. We show that steering methods differ mainly in how they couple two geometric effects: changing a token's angular alignment with a concept direction and changing its hidden-state norm. Across seven language models, we find that concepts are represented primarily in angular structure, supporting the motivation for spherical methods, but that norm remains important for the stability and downstream effects of steering. Our results explain why interventions with similar concept-level effects can behave differently, and suggest that activation steering should be parameterized by interpretable angular and radial components of the intervention, rather than by a single additive coefficient that entangles these two effects.

Georgii Aparin, Tatiana Gaintseva

Huawei Noah’s Ark Lab · Queen Mary University of London

Language Model Steering Language Modeling Causal Interventions in Language Models Activation Steering

Jun 4, 2026cs.SE

Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering

Correctness and readability are key measures of code quality, respectively ensuring functional fidelity and ease of comprehension. While most existing research focuses on improving the correctness of large language models~(LLMs) generated codes, readability remains under-addressed. Enhancing readability through targeted control is challenging due to its subjective nature. In this article, we employ representation engineering~(RepE) as the targeted control method given its characteristics of low data dependency and low computational cost. Prior work on RepE has primarily focused on the targeted control for a single task, but improving the code readability requires the control across multiple tasks. Accordingly we proposes the multitask RepE framework and theoretically discuss the impact of the multitask steering method on the tradeoff between the code readability and correctness. We further provide comprehensive experiments in support. All the relevant implementations are open-source and available upon request.

Huifan Gao, Liuhua He, Yinghui Pan +4

School of Aerospace Engineering, Xiamen University, Xiamen, China · School of Artificial Intelligence, Shenzhen University, Shenzhen, China · College of Computer and Cyber Security, Fujian Normal University, Fuzhou, China +3

Language Model Steering Representation Engineering LLM Code Generation

Jun 4, 2026cs.LG

Steering Vectors are an Adversarial Attack Surface

Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is plug-and-play, users share datasets and precomputed vectors to steer model activations. However, we show that a \emph{stealth data poisoning attack} silently compromises this pipeline. By substituting

4{-}6\%

of tokens in the steering dataset, an attacker can silently align the resulting vector with an anti-refusal direction. This jailbreaks the target model while preserving the intended steering effect on benign prompts. Under this threat model, a malicious actor can distribute an apparently safe bundle containing texts, vectors, and weights, alongside an equivalence certificate that the end-user can verify. We test the attack on two open-weight model families and eight model-attribute combinations, observing that poisoned vectors reach an absolute attack success rate (ASR) of

20{-}55\%

,

+19\%

to

+51\%

over a clean reference. Finally, we find that a refusal-direction orthogonalization defense can recover

{\approx}82\%

of the ASR gap without harming benign behavior.

Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3

1Sapienza University of Rome · 2EPFL

Language Model Steering Adversarial Attacks on LLMs LLM Jailbreak Attacks Data Poisoning Attacks

Jun 2, 2026cs.CL

Expert-Aware Refusal Steering

Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed requests. Recent work has shown that a steering vector can be applied to a dense LLM during inference to effectively suppress refusal behavior, inducing response to harmful requests. We extend this refusal steering method to three open-source Mixture-of-Experts (MoE) LLMs and find that steering performance is uninhibited by the complex routing patterns inherent to the MoE architecture. We then propose two expert-aware refusal steering methods that leverage refusal-specific expert routing patterns and expert-specific steering directions to suppress normal refusal behavior. We find that refusal behavior can be effectively steered based on the output of a single expert. Our results show that refusal signals captured by steering methods differ from expert routing behavior, suggesting a substantial role for attention in MoE refusal behavior.

Anna C. Marbut, Daniel R. Olson, Travis J. Wheeler

Department of Interdisciplinary Studies University of Montana Missoula, MT, USA · Department of Pharmacy Practice & Science University of Arizona Tucson, AZ, USA · European Bioinformatics Institute European Molecular Biology Laboratory Wellcome Genome Campus, Hinxton, United Kingdom

Mixture-of-Experts Language Models Language Model Steering LLM Safety Alignment LLM Refusal Behavior Expert Routing Refusal Behavior in Language Models

Jun 2, 2026cs.CL

Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces, leaving how the model thinks implicit. In this paper, we propose Agentic Chain-of-Thought Steering (ACTS), which formulates reasoning steering as a Markov decision process where a controller agent adaptively steers a frozen reasoner during inference. At each step, the controller observes the reasoning trace and remaining thinking budget, then issues a steering action consisting of a reasoning strategy and a steering phrase that initiates the next reasoner step. This enables budget-aware strategy control for efficient reasoning while preserving the reasoner's generation continuity. We initialize the controller agent from our constructed synthetic steering trajectories with multi-budget augmentation, and further optimize it via reinforcement learning with budget-conditioned reward shaping. Experiments across multiple benchmarks show that ACTS matches full-thinking performance with substantial token savings, and enables controllable accuracy-efficiency trade-offs across different reasoners and tasks. The code is available at https://github.com/Andree-9/ACTS.

Yu Xia, Zhouhang Xie, Xin Xu +4

University of California San Diego1 · Intuit AI Research2

Language Model Steering CoT Reasoning Efficient Language Model Reasoning Efficient Language Model Inference LLM Reasoning

May 31, 2026cs.AI

Subliminal Learning Is Steering Vector Distillation

Subliminal learning refers to a student language model acquiring a teacher's traits (e.g. a system-prompted preference for owls) when fine-tuned on the teacher's outputs, despite the outputs being semantically unrelated to those traits. It remains poorly understood how data without semantic meaning can transfer specific semantic traits. In this work, we show that subliminal learning is mediated by a single steering vector, i.e. a vector added to the model's activations. Across two open-source models, we find that the teacher's system prompt is well approximated by a steering vector, and that the student's behavior is driven by learning an aligned vector over fine-tuning. System prompts that are not well approximated by steering vectors are not subliminally learned. This is a special case of steering vector distillation, in which a student trained on the outputs of a steered teacher learns to imitate that steering. We demonstrate steering vector distillation on a range of semantic and random vectors. Adding a semantic vector to a model's activations can have both model-independent and model-specific (i.e. non-semantic) effects on its behavior, so generated data that is non-semantic can transmit a vector with semantic effects, enabling subliminal learning. This also explains why subliminal learning does not transfer between models. We find that adaptive optimizers are necessary for subliminal learning in language models: activation gradients on steered data carry a small but consistent component along the steering direction, and non-adaptive optimizers impede this by allowing outlier gradients to dominate.

Camila Blank, Agam Bhatia, Senthooran Rajamanoharan +2

Stanford University

Language Model Steering Subliminal Learning Language Model Distillation Teacher-Student Learning Activation Steering

May 30, 2026cs.AI

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficiently adaptive when failures and required corrections vary across reasoning states, tasks, and models. To this end, we propose Latent Reward Steering (LRS), an adaptive inference-time framework that promotes cognitive behaviors by optimizing the sparse-autoencoder (SAE) latent states that implicitly carry them. Rather than relying on predefined cognitive behaviors or steering directions derived from them, LRS trains a latent reward model on reasoning traces by final answer correctness to estimate the quality of intermediate latent states. During inference, reward gradients provide state-specific correction directions for fragile latent states, while a reward and confidence gate restricts intervention to states the reward signal flags as fragile. Experiments on multiple reasoning LLM backbones and benchmarks show that \ours consistently improves performance over various baselines, and post-hoc analyses further indicate that \ours implicitly promotes good cognitive behaviors that fix the original reasoning errors. Code is available at: https://github.com/jiakanglee/Latent-Reward-Steering.

Jiakang Li, Guanyu Zhu, Can Jin +8

Rutgers University · South China Agricultural University · Columbia University +4

Reward Modeling Language Model Steering Activation Steering Inference-Time Guidance LLM Reasoning

May 30, 2026cs.CL

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering Activations), a lightweight adaptation method that learns layer-wise steering vectors. Unlike commonly used steering approaches that rely on contrastive activation differences, SALSA directly optimizes steering vectors using a supervised objective. Across children's speech, multilingual speech, and Mandarin-English code-switching benchmarks, SALSA substantially improves performance over zero-shot inference and speech in-context learning baselines, achieving up to 46.8% relative improvements over zero-shot. Analysis further demonstrates that steering the encoder, particularly the later layers, is more effective than steering the LLM backbone. These findings suggest that steering improves downstream ASR performance by adapting higher-level acoustic and phonetic representations to better align with the pretrained language model representation space, rather than by modifying the decoder itself.

Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng +3

University of Illinois Urbana-Champaign · Korea Advanced Institute of Science and Technology

Language Model Steering Automatic Speech Recognition Speech Language Models

May 29, 2026cs.CL

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines

Sparse Autoencoders (SAEs) have been seen as a promising avenue for exploring the internals of Large Language Models (LLMs) and for steering model output generation. When AxBench - a model steering benchmark - was introduced in Wu et al. (2025), SAEs did not seem to live up to their original hype due to poor steering performance relative to a set of simple baselines. This work serves as a partial rebuttal for Sparse Autoencoders and suggests that the results of Wu et al. (2025) did not do them full justice. We find that Sparse Autoencoders can, in fact, perform close to on par with the reference LoRA performance on the AxBench benchmark, when features are selected and labelled with our supervised pipeline. We also find that our pipeline selects features that are surprisingly causal of their identified labels when using only its interpretability-based components. Lastly, we present evidence that high sparsity (low l0) may not be crucial for successful steering based on interpretability, which is in contrast to the earlier findings in Wang et al. (2025).

Mikkel Godsk Jørgensen, Lars Kai Hansen

DTU Compute · Technical University of Denmark

Language Model Steering LLM Interpretability Sparse Autoencoders

May 28, 2026cs.CL

Cross-Lingual Steering for Figurative Language Generation

Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reusable across languages is unclear. Using activation steering as a probe, we estimate a direction for a figurative category from figurative--literal activation differences in one language and apply it during generation. Across five figurative categories, six languages, and four multilingual LLMs, these directions steer reliably within their own language, most robustly for metaphor and simile. More importantly, they transfer across languages: a direction learned in one increases the target behavior when applied to another, with German among the most receptive targets. Going further, directions assembled from other languages can match or even surpass a target language's own native direction, while removing this shared component weakens native steering. Together, these results provide direct evidence of a reusable but target-dependent cross-lingual signal for figurative generation.

Linfeng Liu, Tiffany Zhan, Louie Hong Yao +2

Department of Computer Science, University of Cincinnati · School of Computer Science, Carnegie Mellon University · Independent Researcher

Multilingual Language Models Language Model Steering Activation Steering Text Generation Cross-Lingual Transfer

May 28, 2026cs.CL

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing methods often rely on fixed steering directions or task-specific intervention modules, making them difficult to adapt to fine-grained concepts and compositional constraints. We propose UniSteer, a text-guided activation flow matching model that learns a conditional distribution over residual-stream activations from natural-language conditions. Instead of fitting a separate intervention for each target behavior, UniSteer learns a universal conditional velocity field in activation space. At inference time, UniSteer performs flow inversion by partially transporting a source activation toward a latent state and regenerating it under a target textual condition before injecting it back into the frozen LLM. The same conditional model supports activation-space classification by selecting the textual label with the lowest reconstruction energy. Experiments on three target LLMs show that UniSteer provides a unified interface across behavioral control, truthfulness steering, fine-grained concept steering, multi-constraint instruction following, and activation-space classification.

Yingdong Shi, Ruiming Zhang, Changming Li +4

ShanghaiTech University

Flow Matching Language Model Steering Activation Steering

May 28, 2026cs.CL

Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning

Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features that are graded. We introduce a method for causal intervention on continuous variables: given activation vectors paired with a graded target variable, we localize a low-dimensional direction for that variable and use this direction to edit a vectors toward counterfactual target values. We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias (which reflects which syntactic structures tend to follow a given verb). We show that verb bias is causally represented in steering vectors extracted from large language models: counterfactual edits to verb bias systematically shift downstream structural preferences. Verb bias has also previously been linked to in-context learning; in further analyses, we find that steering vectors encode error signals that could drive the error-driven update behavior seen in in-context learning but that these aspects of the steering vectors are not causally used in downstream production. Overall, these results show causal interventions can be applied to continuous variables, though connecting continuous variables to in-context learning remains a challenge.

Zhenghao Herbert Zhou, R. Thomas McCoy, Robert Frank

Department of Linguistics Yale University New Haven, CT 06511, USA

Language Model Steering Causal Reasoning in Language Models Causal Interventions in Language Models Causal Intervention

May 27, 2026cs.CL

Sense Representations Are Inducible Interfaces

Sense representations (explicit, per-token meaning decompositions) are useful for disambiguation, steering, and cross-lingual alignment, but existing approaches require models to be pretrained with sense structure baked in. We introduce ACROS, which induces an explicit sense pathway into a frozen pretrained decoder LM through a gated residual addition. On SmolLM2-360M, ACROS preserves base LM quality while supporting three uses of the same induced variables: zero-shot word-sense disambiguation (64.95 F1 on Raganato ALL, competitive with the WordNet first-sense heuristic), low-KL lexical steering across 5,161 CoInCo cases where a simple non-oracle proxy recovers about 90% of positive shifts, and SENSIA cross-lingual adaptation to four languages (mean R@1 0.988, target FLORES PPL 7.94). ACROS makes sense representations an inducible interface for ordinary pretrained LMs.

Jan Christian Blaise Cruz, Alham Fikri Aji

MBZUAI · SEACrowd

Language Model Steering Language Modeling

May 27, 2026cs.CL

Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost

Post-trained language-model assistants are often optimized to avoid under-answering, encouraging complete, helpful, cautious, and proactive responses. We ask whether this optimization creates asymmetric controllability costs: when users explicitly request narrower answers, which assistant behaviors remain suppressible, and which continue to shape the response? We study this problem as boundary-suppression asymmetry. Prompt-side probes across multiple high-level response dimensions suggest a selective cost, concentrated around `too-much assistant' directions such as over-completion, extra help, and anti-underanswering. Using controlled assistant-policy variants derived from a shared base model, we find that anti-underanswering policies are harder to pull back than the baseline under matched boundary-control evaluations, while minimal-boundary variants generally avoid this anti-side upward shift in the direct boundary-control comparisons. Mechanism-oriented probes point beyond longer default outputs, pure EOS failure, uncertainty compensation, and local continuation bias, while robustness checks preserve the main anti-over-baseline ordering under shared-system and larger-scale settings. The evidence supports a mixed planning/stopping account, where content-budget overshoot and continuation persistence jointly make boundary correction harder. Overall, post-training may create direction-specific controllability costs: some helpful assistant tendencies remain easy to invoke, yet harder to locally suppress.

Jiarui Han

Language Model Steering Language Model Post-Training

May 24, 2026cs.LG

Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering

Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention transformations without learning an explicit geometry over paths in activation space. Freshly introduced geometry-aware manifold methods do learn such a geometry, but require labelled class centroids together with prescribed cyclic or sequential structure. These assumptions restrict where manifold steering can be applied, since existing constructions require labelled centroids and compatible boundary conditions. We recast manifold steering more broadly as \textbf{Riemannian geodesic computation} on activation space, recovering linear and labelled-spline steering as geodesics under particular choices of metric. A principled metric within this framework is the output-space Hellinger distance pulled back to activations; we approximate this with a learned encoder trained on output distances over a small concept-token schema - no per-prompt labels, no topology prior, and no per-task curve fitting. Empirically, the method reliably drives the model onto the target class across all tasks in a standard four-task language-model arithmetic benchmark, while following more behaviourally natural trajectories than baselines on smaller output spaces. We thereby provide a unified Riemannian framework for manifold steering together with a schema-supervised, label-free instantiation that operates without labelled centroids or prescribed boundary conditions.

Narmeen Oozeer, Shivam Raval, Philip Quirke +4

Martian · Harvard University · Thoughtworks +1

Language Model Steering Representation Steering Riemannian Geometry Representation Geometry in Language Models

May 21, 2026cs.CL

DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge

Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge remains uneven across regions and languages. We present the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, where we apply activation steering to multilingual LLMs using language vectors extracted from parallel FLORES data. Our method performs inference-time adaptation by adding language-specific steering vectors to the residual stream at a selected transformer layer, without any parameter updates. We participated in both the short-answer (SAQ) and multiple-choice (MCQ) tracks; however, only our MCQ submission received an official score. In the official MCQ track, we achieved 86.96% accuracy, ranking 7th out of 17 teams. To better understand system behavior, we conduct post-hoc analyses on the shared-task MCQ and SAQ settings. These analyses show that activation steering yields modest and heterogeneous improvements on cultural reasoning: gains are strongly layer-sensitive, vary substantially across language-region pairs, with some configurations even degrading performance, and interact with prompt formulation, comparing generic and culturally conditioned prompts. Our findings suggest that prompt design and activation steering should be jointly optimized for culturally aware multilingual inference.

Yusser Al Ghussin, Daniil Gurgurov, Yasser Hamidullah +3

German Research Center for Artificial Intelligence (DFKI GmbH) · Saarland Informatics Campus, Saarbrücken, Germany · Barcelona Supercomputing Center (BSC-CNS), Barcelona, Catalonia, Spain

Multilingual Language Models Multilingual Language Model Evaluation Language Model Steering Cultural Knowledge in Language Models

May 21, 2026cs.LG

Steered Generation via Gradient-Based Optimization on Sparse Query Features

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a high-fidelity site for precise control, hypothesizing that manipulating the attention mechanism itself offers sharper steerability than general state interventions. We introduce Prototype-Based Sparse Steering, a framework that applies Sparse Autoencoders (SAEs) specifically to query activations, to decompose them into interpretable features, then apply gradient-based optimization during inference to align the sparse representation with class prototypes of target behaviors. To validate this architectural insight, we first analyze the mechanism in Textualized Gridworld, a controlled environment for verifiable planning constraints. We demonstrate that optimizing sparse query features enables effective navigation of rigid planning requirements (i.e., safe vs. short paths), confirming the method's ability to satisfy objective rules. We then demonstrate the framework's versatility by training SAEs on a high-dimensional educational domain, where the framework steers the cognitive complexity of feedback (i.e., Bloom's Taxonomy). Our experiments establish that sparse query representations provide the necessary disentanglement for unified, interpretable control over both logical planning and stylistic nuance.

Sumanta Bhattacharyya, Pedram Rooshenas

Department of Computer Science University of Illinois Chicago

Constrained Motion Planning Language Model Steering Large Language Model-Guided Optimization Sparse Autoencoders Activation Steering

May 21, 2026cs.CL

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on English-only data, and steering layers are chosen heuristically. We address these limitations by advancing a principled, mechanistic account of multilingual language steering with SAEs. First, we show that training SAEs on multilingual data consistently strengthens cross-lingual representations and yields more reliable, quality-preserving language control across layers and model families. Second, we introduce an \emph{a priori} steering layer-selection rule based on the intersection of multilingual alignment and language separability, which predicts effective intervention depths without exhaustive layerwise search. We evaluate our approach on LLaMA-3.1-8B and Gemma-2-9B across machine translation and cross-lingual summarization (CrossSumm), using SpBLEU, ROUGE-L, COMET, and LaSE. Our results show that multilingual SAEs combined with intersection-selected layers stabilize the trade-off between language identification accuracy and generation quality, providing a principled, predictive, representation-level account of multilingual SAE steering.

Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel +3

Saarland University · German Research Center for Artificial Intelligence (DFKI) · Centre for European Research in Trusted AI (CERTAIN) +1

Multilingual Language Models Language Model Steering Sparse Autoencoders Cross-Lingual Transfer

May 20, 2026cs.LG

Manifold-Guided Attention Steering

Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possible approach to improve reasoning consistency is through activation steering. However, existing activation steering approaches apply fixed, pre-computed correction vectors, ignoring where the model currently sits along its generation trajectory; the result is indiscriminate perturbation that disrupts already-correct steps as freely as erroneous ones. We propose Manifold-Guided Attention Steering (MAGS), a trajectory-aware inference-time intervention grounded in a geometric observation: the output activations of specific attention heads diverge from a low-dimensional correctness manifold at the point of error, and this deviation compounds through subsequent steps. For each identified attention head, we learn a low-dimensional subspace from contrastive pairs of correct and incorrect traces that capture the directions along which error behavior deviates from correct behavior. During inference, we monitor each head's proximity to this manifold and apply a targeted projection correction when deviation exceeds a learned threshold, steering the attention output back toward the correct subspace before the error propagates. MAGS consistently outperforms both unsteered baselines and static steering approaches across benchmarks spanning mathematical reasoning (MATH-500, GSM8K), code generation (HumanEval, MBPP), and molecular generation (SMILES), suggesting that correctness manifolds are a general feature of LLM attention geometry.

Ian Li, Kapilesh Guruprasad, Raunak Sengupta +3

University of California, San Diego

Language Model Steering Self-Attention Activation Steering LLM Reasoning

May 20, 2026cs.CL

How Far Will They Go? Red-Teaming Online Influence with Large Language Models

As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is critical for information integrity. In pursuit of this goal, we focus on locally deployed open-source LLMs, as opposed to frontier API-only models, given their superior alignment with the operational constraints of privacy-conscious malicious actors deployed in social media environments. We introduce an empirical red-teaming framework for measuring LLM Overton Windows (OWs), defined as the range of political opinions a model can reliably express on controversial topics, and for quantifying how simple natural-language jailbreaks expand that range. We evaluate more than 30 LLMs spanning 10 model families and five countries of origin. We find systematic asymmetries in political expressivity: open-source LLMs are typically more willing to generate left-leaning social media content, OWs tend to contract inversely to model size, and regional differences are substantial despite uneven representation in the open-source ecosystem. Jailbreak potency also varies sharply across model families, motivating a workflow for identifying effective combinations of jailbreak techniques. Taken together, our results establish a practical framework for auditing the political steerability of open-source LLMs and for helping future researchers design stronger countermeasures against LLM-enabled influence campaigns.

Daniel C. Ruiz, Anna Serbina, Ashwin Rao +2

Information Sciences Institute University of Southern California Los Angeles, CA, USA

Language Model Steering LLM Auditing Adversarial Attacks on LLMs Political Bias in Language Models LLM Red Teaming

May 20, 2026cs.AI

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy

Language models are often sycophantic: they agree with a user's stated opinion whether or not it is correct. Prior work has shown that this trait can be controlled by steering a model with a sycophancy persona vector (Chen et al., 2025). Such vectors, however, are extracted from data about sycophancy itself. We ask whether we can instead reuse existing vectors for general roles---Skeptic, Judge, Devil's Advocate---that were extracted without targeting sycophancy at all. On Gemma 2 27B and Qwen 3 32B, we compare these role vectors with a purpose-built Contrastive Activation Addition (CAA) sycophancy vector on a largely held-out, counterbalanced PhilPapers benchmark, using task-specific coefficient tuning on a separate split of sycophancy data. The selected "critical" roles achieve, on average, about 68% (Gemma) and 98% (Qwen) of CAA's reduction in the sycophancy logit. Less agreement does not mean more factual errors on the probes we checked: on 16 true and false factual claims, Qwen steered by the Skeptic or Judge vector still gives the correct answer in all 16 cases, matching the unsteered model and CAA. "Conformist" roles do not reliably produce the opposite effect. Role vectors also have low absolute cosine similarity with the measured CAA direction at the layer we steer; they are geometrically separate interventions, although this does not by itself show that they act through distinct downstream mechanisms. Together, these results show that general persona vectors can help mitigate sycophancy in LLMs, even when extracted without sycophancy-specific labels. Code: https://github.com/vkmk1/Sycophancy-Steering Results: https://github.com/kelkarI/sycophancy-clean-results

Ishaan Kelkar, Vikram Kakaria, Nebras Alam +3

University of Toronto, Toronto, Canada · Princeton University, Princeton, USA · Purdue University, West Lafayette, USA +3

LLM Sycophancy Language Model Steering Activation Steering

May 20, 2026cs.LG

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering

Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they may be under-critical and miss erroneous steps, or over-critical and reject correct reasoning. We refer to this tendency to be overly lenient or overly critical as verifier strictness. In this work, we study whether verifier strictness can be controlled through hidden-state intervention. We uncover a verification-specific hidden-state signal: in step-wise verification, a verifier's tendency to accept or reject a solution step is encoded near the boundary of the corresponding verification paragraph. Exploiting this signal, we show that hidden-state steering can directly modulate verifier strictness without fine-tuning. However, uniform steering induces a trade-off between error detection and correctness certification. To address this, we propose VerifySteer, which exploits latent correctness signals for sample-level routing and selectively intervenes on paragraph boundaries. Experiments on ProcessBench and Hard2Verify show that VerifySteer outperforms prompt optimization and activation steering baselines, and is competitive with self-consistency while requiring 4-7x less inference compute. VerifySteer is also complementary to verification fine-tuning, providing further gains on top of fine-tuned verifiers. The code is available at https://github.com/YefanZhou/VerifySteer.

Yefan Zhou, Yilun Zhou, Austin Xu +3

Dartmouth College · Datadog AI Research · Salesforce AI Research

Language Model Steering Activation Steering Reasoning Verification

May 19, 2026cs.CR

Adaptive Probe-based Steering for Robust LLM Jailbreaking

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of steering strength, limiting their robustness and effectiveness. In this paper, we leverage the idea of model extraction to guide the learned steering vectors to approximate the ideal one and propose tuning the steering strength adaptively based on contrastive activations' statistics. Experiments demonstrate that our method notably improves the effectiveness and robustness of probe-based steering, without any extra contrastive prompts or laborious manual tuning. Being an attack paper, this paper focuses on revealing the breakdown of fortified LLMs, raising the average harmfulness score from 6% to 70%. Our code is available at https://github.com/fhdnskfbeuv/adaptiveSteering.

Junxi Chen, Junhao Dong, Xiaohua Xie

School of Computer Science and Engineering, Sun Yat-Sen University, China · Nanyang Technological University, Singapore.

Language Model Steering Adversarial Attacks on LLMs LLM Jailbreak Attacks Adversarial Robustness of Language Models Activation Steering

May 17, 2026cs.LG

FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers

Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation space is Euclidean. We show this assumption fails drastically: the local geometry induced by the model's own output behavior -- the Fisher information metric of the softmax layer, pulled back through the Jacobian of subsequent layers -- deviates from the Euclidean metric by over 97% in relative spectral norm on GPT-2, with an effective dimensionality of only 2--17% of the ambient space. From this pullback Fisher metric, we derive a closed-form steering equation that identifies the minimum-distortion direction for any target concept, yielding a closed-form optimal direction at each point that can be applied iteratively without manifold fitting or data-driven geometry estimation. We call the resulting framework FishBack. The metric admits a layer-wise recursive decomposition, which reveals that existing methods -- CAA, ActAdd, ITI, and others -- each implicitly adopt a particular approximate metric, and that their performance gaps are quantitatively predicted by a single spectral diagnostic: the ratio of their implicit metric's cost to the Fisher-optimal cost. On GPT-2, iterative pullback steering consistently outperforms all Euclidean baselines across three verb-morphology concepts and four layers, with off-target KL reductions of

1.3\times

--

2.5\times

relative to Euclidean gradient ascent and

1.5\times

relative to CAA at matched concept probability.

Sihan Wang, Jiayi Zhao

South China University of Technology

Information Geometry Language Model Steering Representation Steering Activation Steering

May 15, 2026cs.LG

VSPO: Vector-Steered Policy Optimization for Behavioral Control

Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level of technical expertise in its response. In practice, a base model may exhibit a desired behavior very rarely or not at all. Thus, endowing the model with a target behavior creates a sparse behavioral reward bottleneck. To address such multi-objective problems, we introduce Vector-Steered Policy Optimization (VSPO) which employs a steering vector associated with the target behavior to control the behavior intensity of the generated rollouts. VSPO is obtained by modifying GRPO to sample rollouts with varying steering intensities. This process can be interpreted as an on-policy latent self-distillation procedure where the model internalizes its steering vector. By varying steering intensities, VSPO upsamples rare behaviors and enriches rollout diversity, which alleviates the sparse reward issue and provably accelerates the policy optimization. Through comprehensive theory and experiments, we establish that VSPO has favorable properties compared to vanilla reward shaping and other alternative approaches. Specifically, under a bandit abstraction, VSPO provably achieves better iteration complexity than reward-shaped GRPO when the steering-induced distributions are sufficiently aligned with the target behavior. We evaluate VSPO across multiple reasoning benchmarks, including MATH and MMLU-Pro, for four target behaviors: explanation expertise, confidence expression, robustness to misleading context, and response verbosity. Our results show that VSPO consistently improves the control along target behavior while maintaining or improving task accuracy compared with reward shaping, teacher-trace distillation, and guidance-based baselines.

Xuechen Zhang, Zijian Huang, Kai Yang +3

University of Michigan

Language Model Steering RL for Language Model Reasoning Group Relative Policy Optimization Multi-Objective Language Model Alignment On-Policy Distillation Sparse-Reward RL

May 14, 2026cs.LG

Selective Safety Steering via Value-Filtered Decoding

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using a safety reward. However, existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model. Such unnecessary interventions are undesirable, as they can distort key properties of the base model such as helpfulness, fluency, style, and coherence. We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses. Our approach filters tokens using a value-based safety criterion and provides an explicit bound on the probability of false interventions. A single threshold hyperparameter controls this bound, allowing practitioners to trade off higher rates of unnecessary intervention for better output safety. Across multiple datasets and experiments, we show that our value-filtered decoding method outperforms existing baselines, achieving better trade-offs between safety, helpfulness, and similarity to the base model.

Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh +2

Department of Electrical and Computer Engineering, Technion IIT, Israel · Department of Statistics, University of Oxford, Oxford, UK · OATML, Department of Computer Science, University of Oxford, Oxford, UK +1

Language Model Decoding Language Model Steering Safety Filtering LLM Safety

May 12, 2026cs.LG

WriteSAE: Sparse Autoencoders for Recurrent State

We introduce WriteSAE, a sparse autoencoder for the matrix updates written into recurrent language-model state. In Gated DeltaNet, Mamba-2, and RWKV-7, each token writes a matrix-shaped update to a recurrent cache; a residual-stream SAE has vector-shaped atoms and cannot replace that update directly. WriteSAE learns rank-1 matrix atoms with the same shape as the model's own write. This lets us test a direct replacement: at positions where the SAE activates an atom, we remove the model's write, insert the atom scaled by its SAE activation, and continue the forward pass. The atom gives a closer final token distribution than deleting the write on 92.4% of evaluated positions; averaged per atom, the rate is 89.8%. For Gated DeltaNet, a formula using the forget gate, read query, and output embedding predicts the resulting logit change with

R^2 = 0.98

. The same replacement test transfers to Mamba-2-370M at 88.1%. In generation, the formula chooses a write direction; writing it into three consecutive cache positions at

3\times

the norm of the model's write makes tokens initially ranked 100--1000 by the unmodified model appear in 100% of continuations, up from 33.3%. To our knowledge this is the first cache-level steering intervention reported in a state-space or hybrid recurrent layer.

Jack Young

Indiana University

Language Model Steering Sparse Autoencoders Language Modeling State Representation Learning Causal Interventions in Language Models