English
Related papers

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

200 papers

Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no explicit handle for…

Machine Learning · Computer Science 2026-05-12 Mingxu Zhang , Yuhan Li , Lujundong Li , Dazhong Shen , Hui Xiong , Ying Sun

Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly valuable tools to characterize and control LLMs' behavior,…

Computation and Language · Computer Science 2026-01-19 Michel Frising , Daniel Balcells

A key challenge in AI alignment is guiding large language models (LLMs) to follow desired behaviors at test time. Activation steering, which modifies internal model activations during inference, offers a potential solution. However, prior…

Machine Learning · Computer Science 2025-03-04 Reza Bayat , Ali Rahimi-Kalahroudi , Mohammad Pezeshki , Sarath Chandar , Pascal Vincent

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

Computation and Language · Computer Science 2026-04-21 Gorjan Radevski , Kiril Gashteovski , Giwon Hong , Carolin Lawrence , Goran Glavaš

Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative thinking. However, these models often exhibit overthinking (i.e.,…

Artificial Intelligence · Computer Science 2025-06-19 Weixiang Zhao , Jiahe Guo , Yang Deng , Xingyu Sui , Yulin Hu , Yanyan Zhao , Wanxiang Che , Bing Qin , Tat-Seng Chua , Ting Liu

Text style transfer (TST) aims to modify the style of a text without altering its original meaning. Large language models (LLMs) demonstrate superior performance across multiple tasks, including TST. However, in zero-shot setups, they tend…

Computation and Language · Computer Science 2024-10-02 Wen Lai , Viktor Hangya , Alexander Fraser

Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic…

Computation and Language · Computer Science 2026-04-27 Weixu Zhang , Ye Yuan , Changjiang Han , Yuxing Tian , Zipeng Sun , Linfeng Du , Jikun Kang , Hong Kang , Xue Liu , Haolun Wu

The impressive performance of large language models (LLMs) arises from their massive scale and heterogeneous module composition. However, this structural heterogeneity introduces additional optimization challenges. While adaptive optimizers…

Machine Learning · Computer Science 2026-05-08 Ziqing Wen , Zhouyang Liu , Jiahuan Wang , Ping Luo , Li Shen , Dongsheng Li , Tao Sun

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off: imposing a distinctive style often degrades truthfulness.…

Computation and Language · Computer Science 2025-08-08 Chenglei Shen , Zhongxiang Sun , Teng Shi , Xiao Zhang , Jun Xu

Large Language Models (LLMs) demonstrate increasing conversational fluency, yet instilling them with nuanced, human-like emotional expression remains a significant challenge. Current alignment techniques often address surface-level output…

Computation and Language · Computer Science 2025-11-25 Niranjan Chebrolu , Gerard Christopher Yeo , Kokil Jaidka

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…

Computation and Language · Computer Science 2024-11-06 Atakan Seyitoğlu , Aleksei Kuvshinov , Leo Schwinn , Stephan Günnemann

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak…

Cryptography and Security · Computer Science 2025-11-24 Shourya Batra , Pierce Tillman , Samarth Gaggar , Shashank Kesineni , Kevin Zhu , Sunishchal Dev , Ashwinee Panda , Vasu Sharma , Maheep Chaudhary

Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…

Computation and Language · Computer Science 2025-10-16 Arthur Vogels , Benjamin Wong , Yann Choho , Annabelle Blangero , Milan Bhan

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterizations rely on human-written taxonomies, textual descriptions, or manual profiling pipelines--all…

Artificial Intelligence · Computer Science 2026-04-21 Feiyang Kang , Mahavir Dabas , Myeongseob Ko , Ruoxi Jia

Large language models (LLMs) have achieved state-of-the-art performance in a variety of tasks, but remain largely opaque in terms of their internal mechanisms. Understanding these mechanisms is crucial to improve their reasoning abilities.…

Neurons and Cognition · Quantitative Biology 2025-12-15 Xueqi Ma , Jun Wang , Yanbei Jiang , Sarah Monazam Erfani , Tongliang Liu , James Bailey

Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…

Machine Learning · Computer Science 2026-02-13 Weiting Liu , Han Wu , Yufei Kuang , Xiongwei Han , Tao Zhong , Jianfeng Feng , Wenlian Lu