English
Related papers

Related papers: Steering at the Source: Style Modulation Heads for…

200 papers

Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remains challenging, as their internal mechanisms for representing high-level concepts are poorly…

Sound · Computer Science 2026-05-20 Łukasz Staniszewski , Katarzyna Zaleska , Mateusz Modrzejewski , Kamil Deja

Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse user expectations. Current LLM alignment methods, however,…

Artificial Intelligence · Computer Science 2026-02-19 Rongzhi Zhang , Liqin Ye , Yuzhao Heng , Xiang Chen , Tong Yu , Lingkai Kong , Sudheer Chava , Chao Zhang

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities,…

Computation and Language · Computer Science 2025-02-18 Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

Artificial Intelligence · Computer Science 2026-04-02 Marco Valentino , Geonhee Kim , Dhairya Dalal , Zhixue Zhao , André Freitas

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Machine Learning · Computer Science 2025-12-12 Fu-Chieh Chang , Yu-Ting Lee , Pei-Yuan Wu

Inference-time steering aims to alter a large language model's (LLM's) responses without changing its parameters, but a central challenge is identifying the internal modules that most strongly govern the target behavior. Existing approaches…

Computation and Language · Computer Science 2025-10-02 Li-Ming Zhan , Bo Liu , Chengqiang Xie , Jiannong Cao , Xiao-Ming Wu

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

Artificial Intelligence · Computer Science 2026-05-26 Ciarán Walsh , Emilio Barkett

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. This limitation is particularly problematic in ordinal…

Artificial Intelligence · Computer Science 2026-02-04 Eric Yang , Jong Ha Lee , Jonathan Amar , Elissa Ye , Yugang Jia

Large Language Models (LLMs) are widely used by software engineers for programming tasks. However, research shows that LLMs often lack a deep understanding of program semantics. Even minor changes to syntax, such as renaming variables, can…

Computation and Language · Computer Science 2025-10-06 Francesca Lucchetti , Arjun Guha

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We show that many capabilities are highly localized to small subsets of attention heads within…

Computation and Language · Computer Science 2026-03-05 Anna Bair , Yixuan Even Xu , Mingjie Sun , J. Zico Kolter

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Artificial Intelligence · Computer Science 2026-04-10 Niklas Herbster , Martin Zborowski , Alberto Tosato , Gauthier Gidel , Tommaso Tosato

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)…

Computation and Language · Computer Science 2026-05-13 Jiaqi Chen , Ming Wang , Tingna Xie , Shi Feng , Yongkang Liu

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

Computation and Language · Computer Science 2025-09-16 Alina Klerings , Jannik Brinkmann , Daniel Ruffinelli , Simone Ponzetto

Pre-trained language models (PLM) have demonstrated their effectiveness for a broad range of information retrieval and natural language processing tasks. As the core part of PLM, multi-head self-attention is appealing for its ability to…

Computation and Language · Computer Science 2022-04-07 Shanshan Wang , Zhumin Chen , Zhaochun Ren , Huasheng Liang , Qiang Yan , Pengjie Ren

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Computation and Language · Computer Science 2024-10-31 Rishabh Adiga , Besmira Nushi , Varun Chandrasekaran

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi