Language Model Steering

Follow this topic Ask about this topic

Language model steering studies how to make a pretrained model change a particular behavior—such as tone, refusal, truthfulness, reasoning, or language—without necessarily retraining its weights. Common approaches add contrastive activation vectors, target sparse features or specific neurons and attention heads, or adapt interventions to the prompt and the model’s evolving state; other methods guide logits, decoding, or agent-level decisions. Researchers evaluate these methods on tasks ranging from safety and factuality to personalization, multilingual generation, and reasoning, measuring both target behavior and preservation of general capabilities. A central open challenge is reliable, selective control: a behavior may be readable in activations yet resist intervention, while steering can cause collateral quality loss, prompt sensitivity, or safety trade-offs.

Latest papers

283 papers51 papers in the last four weeks, up 65% on the four weeks before. 0.3% of all new papers.

Apr 22, 2026

Dual-Stance Evaluation of Sycophancy: The Structure of Agreement and the Limits of Intervention

Activation steering can shift LLM behaviour, but standard evaluations do not typically test whether a sycophancy-reduction direction also suppresses agreement with factually correct statements. We introduce dual-stance evaluation, which tests both stances of each topic, and apply it to centroid-difference steering on Llama-3-8B-Instruct. We find a dissociation: the model represents sycophantic and factual agreement in geometrically distinct subspaces, yet the steering direction projects equally onto both and cannot differentially target either. The direction accordingly reduces agreement with factually correct statements (e.g. that the Earth is round) as well as sycophantic ones. All other static properties of the two activation groups are matched, suggesting the behavioural dissociation arises from generation dynamics or from finer-grained structure that residual-stream analysis cannot resolve. The pattern illustrates a general gap: representations that are readable from activations may not be writable through them.

Matthew James Buchan

Independent Researcher, United Kingdom.

LLM Sycophancy Language Model Steering LLM Interpretability Causal Interventions in Language Models

Apr 21, 2026

Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction

Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation methods struggle to support the incremental spatial refinements inherent to the sensemaking process. We identify three critical gaps in existing spatial-textual generation: interaction-revision misalignment, human-LLM intent misalignment, and lack of granular customization. To address these, we introduce Semantic Prompting, a framework for spatial refinement that perceives semantic interactions, reasons about refinement intent, and performs targeted positional revisions. We implemented S-PRISM to realize this framework. The empirical evaluation demonstrated that S-PRISM effectively enhanced the precision of interaction-revision refinement. A user study (

N=14

) highlighted how participants leveraged S-PRISM for incremental formalization through interactive steering. Results showed that users valued its efficient, adaptable, and trustworthy support, which effectively strengthens human-LLM intent alignment.

Xuxin Tang, Ibrahim Tahmid, Eric Krokos +3

Virginia Tech Blacksburg, VA, United States · Department of Defense United States

Grounded Text Generation Language Model Steering Human-AI Collaboration

Apr 20, 2026

The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability

Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure degrades. We show that geometric stability, the consistency of a representation's pairwise distance structure, addresses both. Supervised Shesha variants that measure task-aligned geometric stability predict linear steerability with near-perfect accuracy (

ρ= 0.89

-

0.97

) across 35-69 embedding models and three NLP tasks, capturing unique variance beyond class separability (partial

ρ= 0.62

-

0.76

). A critical dissociation emerges: unsupervised stability fails entirely for steering on real-world tasks (

ρ\approx 0.10

), revealing that task alignment is essential for controllability prediction. However, unsupervised stability excels at drift detection, measuring nearly

2\times

greater geometric change than CKA during post-training alignment (up to

5.23\times

in Llama) while providing earlier warning in 73% of models and maintaining a

6\times

lower false alarm rate than Procrustes. Together, supervised and unsupervised stability form complementary diagnostics for the LLM deployment lifecycle: one for pre-deployment controllability assessment, the other for post-deployment monitoring.

Prashant C. Raju

Language Model Steering LLM Reliability Representation Drift Drifting Models Language Model Auditing

Apr 19, 2026

Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering

Accurate comprehension and controllable generation of emotion and rhetoric are pivotal for enhancing the reasoning capabilities of large language models (LLMs). Existing studies mostly rely on external optimizations, lacking in-depth exploration of internal representation mechanisms, thus failing to achieve fine-grained steering at the neuron level. A handful of works on neurons are confined to emotions, neglecting rhetoric neurons and their intrinsic connections. Traditional neuron masking also exhibits counterintuitive phenomena, making reliable verification of neuron functionality infeasible. To address these issues, we systematically investigate the neurons representation mechanisms and inherent associations of 6 emotion categories and 4 core rhetorical devices. We propose a neuron identification framework that integrates multi-dimensional screening, and design an adaptive masking method incorporating dynamic filtering, attenuation masking, and feedback optimization, enabling reliable causal validation of neuron functionality.Through neuron regulation, we achieve directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons. Experiments on 5 commonly used datasets validate the effectiveness of our method, providing a novel paradigm for the fine-grained steering of emotion and rhetoric expressions in LLMs.

Li Zheng, Xin Zhang, Shuyi He +5

Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China · Ant International · School of Computing Technologies, RMIT University, Australia

Language Model Steering LLM Interpretability Causal Interventions in Language Models

Apr 17, 2026

MidSteer: Optimal Affine Framework for Steering Generative Models

Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a comprehensive theoretical framework. In this paper, we bridge this gap by formalizing the theory of concept steering. First, we establish a link between steering and affine concept erasure, proving that the standard approach for removing unwanted behaviors is a special case of LEACE (a closed-form method for affine erasure). Next, we formulate a principled theoretical framework for concept switching, LEACE-Switch, and characterize the assumptions under which it provides an optimal affine solution. Building on this analysis, we then introduce MidSteer (Minimal Disturbance concept Steering), a more general affine framework for concept manipulation that relaxes these assumptions and enables directed, minimal-disturbance transformations. We demonstrate that MidSteer performs favorably across a range of tasks, modalities, and architectures, including vision diffusion models and large language models.

Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4

Queen Mary University of London, London, UK · Huawei Noah’s Ark, London, UK · QuantumLight Capital, London, UK +2

Language Model Steering Generative Modeling Activation Steering Concept Erasure

Apr 16, 2026

Predicting Where Steering Vectors Succeed

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer diagnostic that repurposes the logit lens as a predictor of steering vector effectiveness. The key measure,

A_{\mathrm{lin}}

, applies the model's unembedding matrix to intermediate hidden states, requiring no training. Across 24 controlled binary concept families on five models (Pythia-2.8B to Llama-8B), peak

A_{\mathrm{lin}}

predicts steering effectiveness at

ρ= +0.86

to

+0.91

and layer selection at

ρ= +0.63

to

+0.92

. A three-regime framework explains when difference-of-means steering works, when nonlinear methods are needed, and when no method can work. An entity-steering demo confirms the prediction end-to-end: steering at the LAP-recommended layer redirects completions on Gemma-2-2B and OLMo-2-1B-Instruct, while the middle layer (the standard heuristic) has no effect on either model.

Jayadev Billa

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

Apr 16, 2026

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

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

Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3

University of California, Los Angeles

Language Model Steering LLM Safety Hallucination Mitigation Activation Steering

Apr 15, 2026

Psychological Steering of Large Language Models

Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions. Thus, we introduce a psychological steering framework that performs unbounded, fluency-constrained sweeps in semantically calibrated units. Our method derives and calibrates residual-stream injections using psychological artifacts, and we use the IPIP-NEO-120, which measures the OCEAN personality model, to compare six injection methods. We find that mean-difference (MD) injections outperform Personality Prompting (P

^2

), an established baseline for OCEAN steering, in open-ended generation in 11 of 14 LLMs, with gains of 3.6% to 16.4%, overturning prior reports favoring prompting and positioning representation engineering as a new frontier in open-ended psychological steering. Further, we find that a hybrid of P

^2

and MD injections outperforms both methods in 13 of 14 LLMs, with gains over P

^2

ranging from 5.6% to 21.9% and from 3.3% to 26.7% over MD injections. Finally, we show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering. Nevertheless, they also induce OCEAN trait covariance patterns that depart from the Big Two model, suggesting a gap between learned representations and human psychology.

Leonardo Blas, Robin Jia, Emilio Ferrara

Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089

Language Model Steering Representation Engineering Personality Modeling in Language Models

Apr 15, 2026

From Weights to Activations: Is Steering the Next Frontier of Adaptation?

Post-training adaptation of language models is commonly achieved through parameter updates or input-based methods such as fine-tuning, parameter-efficient adaptation, and prompting. In parallel, a growing body of work modifies internal activations at inference time to influence model behavior, an approach known as steering. Despite increasing use, steering is rarely analyzed within the same conceptual framework as established adaptation methods. In this work, we argue that steering should be regarded as a form of model adaptation. We introduce a set of functional criteria for adaptation methods and use them to compare steering approaches with classical alternatives. This analysis positions steering as a distinct adaptation paradigm based on targeted interventions in activation space, enabling local and reversible behavioral change without parameter updates. The resulting framing clarifies how steering relates to existing methods, motivating a unified taxonomy for model adaptation.

Simon Ostermann, Daniil Gurgurov, Tanja Baeumel +4

Saarland University · German Research Center for Artificial Intelligence (DFKI) · Centre for European Research in Trusted AI (CERTAIN) +6

Online Language Model Adaptation Language Model Steering Inference-Time Adaptation of Language Models Activation Steering

Apr 15, 2026

Beyond Static Personas: Situational Personality Steering for Large Language Models

Personalized Large Language Models (LLMs) facilitate more natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained by limited controllability and high resource demands. Furthermore, their reliance on static personality modeling restricts adaptability across varying situations. To address these limitations, we first demonstrate the existence of situation-dependency and consistent situation-behavior patterns within LLM personalities through a multi-perspective analysis of persona neurons. Building on these insights, we propose IRIS, a training-free, neuron-based Identify-Retrieve-Steer framework for advanced situational personality steering. Our approach comprises situational persona neuron identification, situation-aware neuron retrieval, and similarity-weighted steering. We empirically validate our framework on PersonalityBench and our newly introduced SPBench, a comprehensive situational personality benchmark. Experimental results show that our method surpasses best-performing baselines, demonstrating IRIS's generalization and robustness to complex, unseen situations and different models architecture.

Zesheng Wei, Mengxiang Li, Zilei Wang +1

University of Science and Technology of China · Singapore Management University

Language Model Steering Personality Modeling in Language Models Personalized Language Models

Apr 14, 2026

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering

Simulating Standardized Patients with cognitive impairment offers a scalable and ethical solution for clinical training. However, existing methods rely on discrete prompt engineering and fail to capture the heterogeneity of deficits across varying domains and severity levels. To address this limitation, we propose StsPatient for the fine-grained simulation of cognitively impaired patients. We innovatively capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses. Furthermore, we introduce a Stochastic Token Modulation (STM) mechanism to regulate the intervention probability. STM enables precise control over impairment severity while mitigating the instability of conventional vector methods. Comprehensive experiments demonstrate that StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.

Weikang Zhang, Zimo Zhu, Zhichuan Yang +3

School of Software, Xi’an Jiaotong University · Institute of Data Science, National University of Singapore · College of Computer Science, Sichuan University +1

Large Language Model-Based Role-Play Simulation Language Model Steering Activation Steering

Apr 13, 2026

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering large language models (LLMs). However, existing approaches typically require fine-tuning or invasive manipulation of internal states, limiting their flexibility and scalability. We propose DeCoVec (Decoding Space based Task Vector), a training-free and non-invasive framework that constructs task vectors directly in the decoding space by leveraging in-context learning (ICL). Specifically, DeCoVec captures the task essence as the difference between the output logit distributions of few-shot and zero-shot prompts, then steers generation by injecting this vector into the decoding process. Experiments across seven LLMs (0.5B--9B) on TruthfulQA, Math-500, and AQUA-RAT show that DeCoVec consistently outperforms standard few-shot baselines, with gains up to +5.50 average accuracy. Further analysis demonstrates that DeCoVec effectively suppresses generation degeneration and logical flaws while exhibiting strong robustness to demonstration ordering, all without incurring additional input token costs. Our method offers a training-free and non-invasive solution for LLM steering without requiring weight updates or auxiliary models.

Feiyang Li, Yile Wang

College of Computer Science and Software Engineering, Shenzhen University

Language Model Steering Task Vectors LLM Inference

Apr 13, 2026

A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities

Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capabilities remains unexplored. We employ the Neuron-based Personality Trait Induction (NPTI) framework to induce Big Five personality traits in LLMs and evaluate performance across six cognitive benchmarks. Our findings reveal that persona induction produces stable, reproducible shifts in cognitive task performance beyond surface-level stylistic changes. These effects exhibit strong task dependence: certain personalities yield consistent gains on instruction-following, while others impair complex reasoning. Effect magnitude varies systematically by trait dimension, with Openness and Extraversion exerting the most robust influence. Furthermore, LLM effects show 73.68% directional consistency with human personality-cognition relationships. Capitalizing on these regularities, we propose Dynamic Persona Routing (DPR), a lightweight query-adaptive strategy that outperforms the best static persona without additional training.

Jiaqi Chen, Ming Wang, Tingna Xie +2

School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · School of Computing and Information Systems, Singapore Management University, Singapore 178902, Singapore · School of Computer and Communication Engineering, Northeastern University, Qinhuangdao 066004, China

Language Model Steering Personality Modeling in Language Models Activation Steering

Apr 13, 2026

From Words to Widgets for Controllable LLM Generation

Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceived as more controllable and transparent than natural language prompting alone.

Chao Zhang, Yiren Liu, Lunyiu Nie +3

Cornell University Ithaca, NY, USA · University of Illinois Urbana-Champaign Champaign, IL, USA · The University of Texas at Austin Austin, TX, USA +1

LLM Prompting Controllable Text Generation Language Model Steering

Apr 9, 2026

ExecTune: Effective Steering of Black-Box LLMs with Guide Models

For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize expensive reasoning into reusable intermediate representations. We study a broad class of such systems, termed Guide-Core Policies (GCoP), in which a guide model generates a structured strategy that is executed by a black-box core model. This abstraction subsumes base, supervised, and advisor-style approaches, which differ primarily in how the guide is trained. We formalize GCoP under a cost-sensitive utility objective and show that end-to-end performance is governed by guide-averaged executability: the probability that a strategy generated by the guide can be faithfully executed by the core. Our analysis shows that existing GCoP instantiations often fail to optimize executability under deployment constraints, resulting in brittle strategies and inefficient computation. Motivated by these insights, we propose ExecTune, a principled training recipe that combines teacher-guided acceptance sampling, supervised fine-tuning, and structure-aware reinforcement learning to directly optimize syntactic validity, execution success, and cost efficiency. Across mathematical reasoning and code-generation benchmarks, GCoP with ExecTune improves accuracy by up to 9.2% over prior state-of-the-art baselines while reducing inference cost by up to 22.4%. It enables Claude Haiku 3.5 to outperform Sonnet 3.5 on both math and code tasks, and to come within 1.7% absolute accuracy of Sonnet 4 at 38% lower cost. Beyond efficiency, GCoP also supports modular adaptation by updating the guide without retraining the core.

Vijay Lingam, Aditya Golatkar, Anwesan Pal +6

AWS AI

Language Model Steering LLM Inference Efficiency Cost-Aware Inference RL for Language Model Reasoning

Apr 9, 2026

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works--specifically, what internal mechanisms steering vectors affect and how this results in different model outputs. To investigate the causal mechanisms underlying the effectiveness of steering vectors, we conduct a comprehensive case study on refusal. We propose a multi-token activation patching framework and discover that different steering methodologies leverage functionally interchangeable circuits when applied at the same layer. These circuits reveal that steering vectors primarily interact with the attention mechanism through the OV circuit while largely ignoring the QK circuit. Freezing all attention scores during steering drops performance by only 8.83% across three model families. A mathematical decomposition of the steered OV circuit further reveals semantically interpretable concepts, even in cases where the steering vector itself does not. Leveraging the activation patching results, we show that steering vectors can be sparsified by up to 85-96% while retaining most performance, and that different steering methodologies agree on a subset of important dimensions.

Stephen Cheng, Sarah Wiegreffe, Dinesh Manocha

University of Maryland, College Park

Language Model Steering LLM Interpretability Representation Steering Attention Mechanisms Circuits in Language Models Refusal Behavior in Language Models

Apr 8, 2026

Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring

Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood. We study activation-based persona vectors representing seven character traits in short-answer generation and automated scoring on the ASAP-SAS benchmark, across three language models spanning dense and mixture-of-experts architectures. Persona steering lowers answer quality overall, with much larger effects on open-ended English Language Arts (ELA) prompts than on factual science prompts. Interpretive and argumentative tasks are particularly sensitive, showing up to 11

\times

larger degradation. On the scoring side, we observe predictable valence-aligned calibration shifts: evil'' and impolite'' scorers grade more harshly, while good'' and optimistic'' scorers grade more leniently. ELA tasks are 2.5-3

\times

more susceptible to scorer personalization than science tasks, and the mixture-of-experts model shows roughly 6

\times

larger calibration shifts than the dense models. To our knowledge, this is the first study to systematically examine the effects of activation-steered persona traits in educational generation and scoring. Our findings highlight the need for task- and architecture-aware calibration when deploying personalized models in educational settings.

Yongchao Wu, Aron Henriksson

Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden

Open-Ended Generation Language Model Steering Language Model Generation Evaluation AI in Education Automated Grading Language Model Calibration+3

Apr 7, 2026

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become increasingly separable with layer depth. This structure already exists in base models, while reasoning training primarily accelerates convergence toward termination-related subspaces rather than introducing new representational organization. While early reasoning steps follow similar trajectories, correct and incorrect solutions diverge systematically at late stages. This late-stage divergence enables mid-reasoning prediction of final-answer correctness with ROC-AUC up to 0.87. Furthermore, we introduce trajectory-based steering, an inference-time intervention framework that enables reasoning correction and length control based on derived ideal trajectories. Together, these results establish reasoning trajectories as a geometric lens for interpreting, predicting, and controlling LLM reasoning behavior.

Lihao Sun, Hang Dong, Bo Qiao +3

Microsoft

LLM Reasoning Representation Geometry in Language Models Language Model Steering

Apr 5, 2026

Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison

Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first comparative analysis of emotion vector extraction methods for SLMs, evaluating 9 models across 5 architectural families (GPT-2, Gemma, Qwen, Llama, Mistral) using 20 emotions and two extraction methods (generation-based and comprehension-based). Generation-based extraction produces statistically superior emotion separation (Mann-Whitney p = 0.007; Cohen's d = -107.5), with the advantage modulated by instruction tuning and architecture. Emotion representations localize at middle transformer layers (~50% depth), following a U-shaped curve that is architecture-invariant from 124M to 3B parameters. We validate these findings against representational anisotropy baselines across 4 models and confirm causal behavioral effects through steering experiments, independently verified by an external emotion classifier (92% success rate, 37/40 scenarios). Steering reveals three regimes -- surgical (coherent text transformation), repetitive collapse, and explosive (text degradation) -- quantified by perplexity ratios and separated by model architecture rather than scale. We document cross-lingual emotion entanglement in Qwen, where steering activates semantically aligned Chinese tokens that RLHF does not suppress, raising safety concerns for multilingual deployment. This work provides methodological guidelines for emotion research on open-weight models and contributes to the Model Medicine series by bridging external behavioral profiling with internal representational analysis.

Jihoon Jeong

Department of Electrical Engineering and Computer Science Daegu Gyeongbuk Institute of Science and Technology (DGIST) ModuLabs

Emotion Representation in Language Models Small Language Models Language Model Steering Activation Steering

Apr 4, 2026

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation of model behaviors by shifting intermediate representations toward a target behavior. Many existing steering methods apply interventions at globally fixed locations in an LLM, effectively treating the optimal intervention location as input-invariant. However, representations relevant to a target behavior can be encoded at different LLM layers depending on the input. Theoretically, we show that different inputs may require steering at different layers to achieve alignment with a given behavior. Empirically, we observe that the most effective layer for steering varies substantially between inputs. Motivated by these observations, we introduce Where to Steer (W2S), a general framework that adaptively selects intervention layers conditioned on the inputs by learning a mapping from input representations to steering layers. Across multiple LLMs and alignment behaviors, W2S consistently outperforms fixed-layer baselines in both in-distribution and out-of-distribution settings. Our findings suggest that input-dependent layer selection is a key design dimension complementary to methods for steering vector extraction.

Soham Gadgil, Chris Lin, Su-In Lee

University of Washington

Language Model Steering Inference-Time Language Model Alignment Activation Steering

Apr 4, 2026

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model activations at inference time, but identifying language-specific directions in the residual stream often relies on multilingual or parallel data that can be expensive to obtain. Sparse autoencoders (SAEs) decompose residual activations into interpretable, sparse feature directions and offer a natural basis for this search, yet existing SAE-based approaches face the same data constraint. We introduce LangFIR (Language Feature Identification via Random-token Filtering), a method that discovers language-specific SAE features using only a small amount of monolingual data and random-token sequences. Many SAE features consistently activated by target-language inputs do not encode language identity. Random-token sequences surface these language-agnostic features, allowing LangFIR to filter them out and isolate a sparse set of language-specific features. We show that these features are extremely sparse, highly selective for their target language, and causally important: directional ablation increases cross-entropy loss only for the corresponding language. Using these features to construct steering vectors for the multilingual generation control task, LangFIR achieves the best average accuracy x BLEU among steering methods across three models (Gemma 3 1B, Gemma 3 4B, and Llama 3.1 8B), three datasets, and twelve target languages, outperforming the strongest monolingual baseline by up to 4.7x and surpassing methods that use parallel data. Our results suggest that language identity in multilingual LLMs is localized in a sparse set of feature directions discoverable with monolingual data. Code is available at https://github.com/JaMussCraft/LangFIR

Sing Hieng Wong, Hassan Sajjad, A. B. Siddique

Department of Computer Science, University of Kentucky, USA · Department of Computer Science, Dalhousie University, Canada

Language Model Steering Multilingual Language Models Text Generation

Apr 3, 2026

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation

Generating diverse, pedagogically valid stories for Arabic early-grade reading assessments requires balancing tight constraints on vocabulary, reading level, and narrative structure against the need to avoid repetitive plots that undermine assessment validity. We investigate noise steering, injecting calibrated Gaussian perturbations into the internal representations of transformer models at inference time, as a training-free diversity method evaluated across five small Arabic-centric language models (7-9B parameters). We compare four injection strategies against high-temperature sampling baselines, measuring diversity, quality, constraint adherence, and reading grade level. Residual stream noise consistently improves narrative diversity with minimal quality or constraint cost and preserves early-grade reading level across all Arabic-centric models. Attention entropy noise injection (AENI) stabilizes the otherwise unreliable attention-logit noise while recovering quality. High-temperature sampling inflates reading grade level and causes catastrophic collapse on several models. We find internal representation-level perturbation to be a more suitable diversity strategy than output-level stochasticity for constrained educational content generation.

Haziq Mohammad Khalid, Salsabeel Shapsough, Imran Zualkernan

American University of Sharjah

Text Generation Diverse Text Generation Controllable Text Generation Language Model Steering Activation Steering

Apr 3, 2026

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ridge regression, we recover meaningful VA axes underlying emotion steering vectors whose projections correlate with human affect ratings across 44,728 words. Steering along these axes produces monotonic control over the affective properties of generated text, and further affords bidirectional control over multiple downstream behaviors (refusal and sycophancy) from a single subspace. These effects replicate across Llama-3.1-8B, Qwen3-8B, and Qwen3-14B. We propose lexical mediation to explain why these effects and prior emotionally framed controls work: refusal and compliance tokens occupy distinct VA regions, and VA steering directly modulates their emission probabilities.

Lihao Sun, Lewen Yan, Xiaoya Lu +3

University of Chicago · Shanghai AI Lab · Harvard University

Emotion Representation in Language Models Language Model Steering Valence-Arousal Modeling

Apr 3, 2026

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Activation steering presupposes that task-relevant behaviors correspond to linear directions in activation space -- directions that should both steer the model and be readable along the unembedding. Function vectors (FVs), extracted as mean differences across ICL demonstrations, are the canonical test case; the prediction: steering and decoding succeed or fail together. Across 12 tasks, 6 models from 3 families, and 4,032 directed cross-template pairs, we find the opposite. FV steering routinely succeeds where the logit lens cannot decode the correct answer at any intermediate layer, while the converse -- decodable without steerable -- is nearly empty (3 of 72). The gap is not representational dialect. A diagonal tuned lens closes 1 of 14 steerable-not-decodable cases; a 2-layer MLP probe with a Hewitt & Liang control closes 5 of 10 via nonlinearly encoded structure but leaves 5 invisible to every decoder tested. Even at

> 0.90

steering accuracy, projecting the FV through the unembedding yields incoherent token distributions: FVs encode computational instructions, not answer directions. A model-family asymmetry sharpens the picture. Mistral FVs rewrite intermediate representations, while Llama and Gemma FVs steer the final output without leaving a logit-lens-visible trace, corroborated by three signals (post-steering deltas, activation-patching recovery, FV norm-transfer correlations). A previously reported negative cosine-transfer correlation dissolves at scale, adding at most

ΔR^2 = 0.011

beyond task identity. These results decompose the linear representation hypothesis into linear decodability and linear steerability and show they come apart opposite to intuition, with implications for safety monitoring: vocabulary-projection tools are blind to FV-style interventions on widely deployed model families.

Mohammed Suhail B Nadaf

Independent

Function Vectors Transformer Interpretability Language Model Steering Activation Steering

Apr 2, 2026

Reliable Control-Point Selection for Steering Reasoning in Large Language Models

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors that can be toggled via prompts, this is straightforward. However, many reasoning behaviors -- such as self-reflection -- emerge spontaneously and resist prompt-level control. Current methods detect these behaviors through keyword matching in chain-of-thought traces, implicitly assuming that every detected boundary encodes a genuine behavioral signal. We show that this assumption is overwhelmingly wrong: across 541 keyword-detected boundaries, 93.3% are behaviorally unstable, failing to reproduce the detected behavior under re-generation from the same prefix. We develop a probabilistic model that formalizes intrinsic reasoning behaviors as stochastic events with context-dependent trigger probabilities, and show that unstable boundaries dilute the steering signal. Guided by this analysis, we propose stability filtering, which retains only boundaries where the model consistently reproduces the target behavior. Combined with a content-subspace projection that removes residual question-specific noise, our method achieves 0.784 accuracy on MATH-500 (+5.0 over the strongest baseline). The resulting steering vectors transfer across models in the same architecture family without re-extraction, improving Nemotron-Research-Reasoning-1.5B (+5.0) and DeepScaleR-1.5B-Preview (+6.0). Code is available at https://github.com/zhmzm/stability-steering.

Haomin Zhuang, Hojun Yoo, Xiaonan Luo +2

University of Notre Dame

Language Model Steering Activation Steering LLM Reasoning Implicit Reasoning in Language Models

Mar 31, 2026

Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models

Existing narrative extraction methods face a trade-off between coherence, interactivity, and multi-storyline support. Narrative Maps supports rich interaction and generates multiple storylines as a byproduct of its coverage constraints, though this comes at the cost of individual path coherence. Narrative Trails achieves high coherence through maximum capacity path optimization but provides no mechanism for user guidance or multiple perspectives. We introduce agenda-based narrative extraction, a method that bridges this gap by integrating large language models into the Narrative Trails pathfinding process to steer storyline construction toward user-specified perspectives. Our approach uses an LLM at each step to rank candidate documents based on their alignment with a given agenda while maintaining narrative coherence. Running the algorithm with different agendas yields different storylines through the same corpus. We evaluated our approach on a news article corpus using LLM judges with Claude Opus 4.5 and GPT 5.1, measuring both coherence and agenda alignment across 64 endpoint pairs and 6 agendas. LLM-driven steering achieves 9.9% higher alignment than keyword matching on semantic agendas (p=0.017), with 13.3% improvement on Regime Crackdown specifically (p=0.037), while keyword matching remains competitive on agendas with literal keyword overlap. The coherence cost is minimal: LLM steering reduces coherence by only 2.2% compared to the agenda-agnostic baseline. Counter-agendas that contradict the source material score uniformly low (2.2-2.5) across all methods, confirming that steering cannot fabricate unsupported narratives.

Brian Felipe Keith-Norambuena, Carolina Inés Rojas-Córdova, Claudio Juvenal Meneses-Villegas +4

Department of Computing and Systems Engineering, Universidad Católica del Norte, Antofagasta, Chile · Department of Industrial Engineering, Universidad Católica del Norte, Antofagasta, Chile · Department of Chemical and Environmental Engineering, Universidad Católica del Norte, Antofagasta, Chile

Language Model Steering Interactive Storytelling

Mar 24, 2026

Steering Code LLMs with Activation Directions for Language and Library Control

Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at inference time. Using a difference-in-means method, we estimate layer-wise steering vectors for five language/library pairs and add them to model hidden states during generation. Across three open-weight code LLMs, these interventions substantially increase generation toward the target ecosystem under neutral prompts and often remain effective even when prompts explicitly request the opposite choice. Steering strength varies by model and target, with common ecosystems easier to induce than rarer alternatives, and overly strong interventions can reduce output quality. Overall, our results suggest that code-style preferences in LLMs are partly represented by compact, steerable structure in activation space.

Md Mahbubur Rahman, Arjun Guha, Harshitha Menon

Iowa State University · Northeastern University · Lawrence Livermore National Laboratory

Language Model Steering Code Language Models Activation Steering Code Generation Representation Geometry in Language Models

Mar 24, 2026

Steering LLMs for Culturally Localized Generation

LLMs are deployed globally, yet produce responses biased towards cultures with abundant training data. Existing cultural localization approaches such as prompting or post-training alignment are black-box, hard to control, and do not reveal whether failures reflect missing knowledge or poor elicitation. In this paper, we address these gaps using mechanistic interpretability to uncover and manipulate cultural representations in LLMs. Leveraging sparse autoencoders, we identify interpretable features that encode culturally salient information and aggregate them into Cultural Embeddings (CuE). We use CuE both to analyze implicit cultural biases under underspecified prompts and to construct white-box steering interventions. Across multiple models, we show that CuE-based steering increases cultural faithfulness and elicits significantly rarer, long-tail cultural concepts than prompting alone. Notably, CuE-based steering is complementary to black-box localization methods, offering gains when applied on top of prompt-augmented inputs. This also suggests that models do benefit from better elicitation strategies, and don't necessarily lack long-tail knowledge representation, though this varies across cultures. Our results provide both diagnostic insight into cultural representations in LLMs and a controllable method to steer towards desired cultures.

Simran Khanuja, Hongbin Liu, Shujian Zhang +4

Carnegie Mellon University · Google DeepMind

Cultural Knowledge in Language Models Cultural Bias in Language Models Language Model Steering LLM Interpretability

Mar 23, 2026

LLM-guided headline rewriting for clickability enhancement without clickbait

Enhancing reader engagement while preserving informational fidelity is a central challenge in controllable text generation for news media. Optimizing news headlines for reader engagement is often conflated with clickbait, resulting in exaggerated or misleading phrasing that undermines editorial trust. We frame clickbait not as a separate stylistic category, but as an extreme outcome of disproportionate amplification of otherwise legitimate engagement cues. Based on this view, we formulate headline rewriting as a controllable generation problem, where specific engagement-oriented linguistic attributes are selectively strengthened under explicit constraints on semantic faithfulness and proportional emphasis. We present a guided headline rewriting framework built on a large language model (LLM) that uses the Future Discriminators for Generation (FUDGE) paradigm for inference-time control. The LLM is steered by two auxiliary guide models: (1) a clickbait scoring model that provides negative guidance to suppress excessive stylistic amplification, and (2) an engagement-attribute model that provides positive guidance aligned with target clickability objectives. Both guides are trained on neutral headlines drawn from a curated real-world news corpus. At the same time, clickbait variants are generated synthetically by rewriting these original headlines using an LLM under controlled activation of predefined engagement tactics. By adjusting guidance weights at inference time, the system generates headlines along a continuum from neutral paraphrases to more engaging yet editorially acceptable formulations. The proposed framework provides a principled approach for studying the trade-off between attractiveness, semantic preservation, and clickbait avoidance, and supports responsible LLM-based headline optimization in journalistic settings.

Yehudit Aperstein, Linoy Halifa, Sagiv Bar +1

Intelligent Systems, Afeka Academic College of Engineering, Tel Aviv 69988, Israel · School of Computer Science, Faculty of Sciences, HIT-Holon Institute of Technology, Holon 58102, Israel

Text Generation Controllable Text Generation Language Model Steering

Mar 22, 2026

Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.

Johnathan Sun, Andrew Zhang

Harvard University

Personality Modeling in Language Models Language Model Steering Activation Steering