Language Model Controllability

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Sparse Internal Control of Language Models
Nov 3, 2026Xizhe ZhangLanguage Model Controllability Language Model Steering
Prior Action Control Causally Alters Language-Model Plasticity
Nov 2, 2026Marc-Andre SchulzLanguage Model Controllability Causal Interventions in Language Models
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Tübingen, Germany · Department of Psychiatry and Neurosciences, Charité – Universitätsmedizin Berlin, Berlin, Germany +1
Prefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
Oct 16, 2026Peter Cho-Ho Lam, Ziyi Wang, Zirui ZhouLanguage Model Controllability Prefix Tuning
Huawei Technologies Canada Co., Ltd.
Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts
Sep 7, 2026Kaicheng Zhang, Jingyi Xiao, Renjun Hu +3LLM Alignment LLM Safety Evaluation
East China Normal University Shanghai, China
Leverage Is Not Reach: A Control-Window Law for Single-Neuron Steering in Language Models
Jun 18, 2026Hongliang LiuLanguage Model Steering Causal Interventions in Language Models
Palo Alto Networks
P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs
Jun 15, 2026Rafael Ferreira, Inês Vieira, Inês Calvo +6Multilingual Language Model Evaluation Social Bias in Language Models
NOVA University of Lisbon, Portugal · NOVA LINCS
Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost
May 27, 2026Jiarui HanLanguage Model Steering Language Model Post-Training
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Mar 8, 2026Yige Li, Wei Zhao, Zhe Li +6Language Model Controllability LLM Safety
Singapore Management University · The University of Melbourne · Fudan University
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Mar 3, 2026Ziwen Xu, Kewei Xu, Haoming Xu +8Language Model Controllability LLM Evaluation
Zhejiang University · Alibaba Group

Nov 3, 2026J/K move · Enter open · S save

Sparse Internal Control of Language Models

Xizhe Zhang

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

Open paper AskPDF arXiv

Language models are increasingly used in text generation, decision support, and automated interaction, creating a need for localized, reversible, and selective control of their behavior. Activation steering demonstrates that internal interventions can alter the behavior of frozen models, but how to select and evaluate compact, multi-site control interfaces remains an open question. I introduce sparse internal control, a framework for steering target behavior by applying inference-time interventions to a small set of internal model nodes. A local target-controllability formulation characterizes candidate site--direction pairs by their behavioral effects and specifies constraints on target recovery, off-target preservation, and intervention energy. Two complementary selectors instantiate this formulation: Driver-OMP selects nodes for sparse reconstruction of a desired behavioral displacement, while Coverage-Driver favors stable coverage across prompts. I propose a six-axis control-evaluation protocol measuring reachability, signed reversal, dose response, feedback controllability, off-target preservation, and held-out reuse. Exploratory experiments on indirect object identification, MMLU multiple-choice question answering, sentiment steering, and refusal steering provide evidence for the feasibility of steering task-defined behavior through sparse internal interventions. The six-axis evaluation characterizes these interventions beyond target movement, revealing distinct control properties that depend on the task and available direction information. Together, the formulation, reference algorithms, and evaluation protocol provide a foundation for the systematic study and development of internal control methods for language models.