English
Related papers

Related papers: Why Steering Works: Toward a Unified View of Langu…

200 papers

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

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

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…

Computation and Language · Computer Science 2026-04-16 Simon Ostermann , Daniil Gurgurov , Tanja Baeumel , Michael A. Hedderich , Sebastian Lapuschkin , Wojciech Samek , Vera Schmitt

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

Machine Learning · Computer Science 2026-01-28 Quy-Anh Dang , Chris Ngo

Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant features, from…

As large language models (LLMs) become increasingly embedded in everyday applications, ensuring their alignment with the diverse preferences of individual users has become a critical challenge. Currently deployed approaches typically assume…

Machine Learning · Computer Science 2024-12-19 Katarzyna Kobalczyk , Claudio Fanconi , Hao Sun , Mihaela van der Schaar

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

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

Computation and Language · Computer Science 2026-04-17 Shiwan Zhao , Zhihu Wang , Xuyang Zhao , Jiaming Zhou , Caiyue Xu , Chenfei Liu , Liting Zhang , Yuhang Jia , Yanzhe Zhang , Hualong Yu , Zichen Xu , Qicheng Li , Yong Qin

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Computation and Language · Computer Science 2024-12-31 Jingyuan Ma , Rui Li , Zheng Li , Lei Sha , Zhifang Sui

As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…

Machine Learning · Computer Science 2026-05-21 Qihao Lin , Guanxu Chen , Dongrui Liu , Jing Shao

We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different…

Computation and Language · Computer Science 2024-04-01 Keiichi Namikoshi , Alex Filipowicz , David A. Shamma , Rumen Iliev , Candice L. Hogan , Nikos Arechiga

Large Language Models (LLMs) are increasingly applied to automate software engineering tasks, including the generation of UML class diagrams from natural language descriptions. While prior work demonstrates that LLMs can produce…

Software Engineering · Computer Science 2026-04-07 Rabia Iftikhar , Andreas Rausch

Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how…

Artificial Intelligence · Computer Science 2026-01-13 Tetiana Bas , Krystian Novak

Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, existing alignment…

Machine Learning · Computer Science 2026-03-03 Jia Zhang , Yao Liu , Chen-Xi Zhang , Yi Liu , Yi-Xuan Jin , Lan-Zhe Guo , Yu-Feng Li

As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies,…

Computation and Language · Computer Science 2024-02-20 Junlong Li , Fan Zhou , Shichao Sun , Yikai Zhang , Hai Zhao , Pengfei Liu

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

Computation and Language · Computer Science 2025-01-09 Hritik Bansal , Ashima Suvarna , Gantavya Bhatt , Nanyun Peng , Kai-Wei Chang , Aditya Grover

As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias,…

Artificial Intelligence · Computer Science 2025-04-23 Anna Karnysheva , Christian Drescher , Dietrich Klakow

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Computation and Language · Computer Science 2024-10-21 Mozhi Zhang , Pengyu Wang , Chenkun Tan , Mianqiu Huang , Dong Zhang , Yaqian Zhou , Xipeng Qiu

Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representations to adjust behavior. Recent work has shown that…

Computation and Language · Computer Science 2025-05-28 Zhengxuan Wu , Qinan Yu , Aryaman Arora , Christopher D. Manning , Christopher Potts