English
Related papers

Related papers: Representation Tuning

200 papers

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of…

Machine Learning · Computer Science 2026-03-13 Eric Bigelow , Daniel Wurgaft , YingQiao Wang , Noah Goodman , Tomer Ullman , Hidenori Tanaka , Ekdeep Singh Lubana

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Machine Learning · Computer Science 2026-02-03 Parmida Davarmanesh , Ashia Wilson , Adityanarayanan Radhakrishnan

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

Computation and Language · Computer Science 2025-10-17 Chao Han , Yijuan Liang , Zihao Xuan , Daokuan Wu , Wei Zhang , Xiaoyu Shen

Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs.…

Computation and Language · Computer Science 2025-12-09 Jungmin Lee , Gwangeun Byeon , Yulhwa Kim , Seokin Hong

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Artificial Intelligence · Computer Science 2026-05-11 Aayush Mishra , Daniel Khashabi , Anqi Liu

Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. While large language models (LLMs) exhibit strong reasoning…

Computation and Language · Computer Science 2025-10-15 Yurui Dong , Luozhijie Jin , Yao Yang , Bingjie Lu , Jiaxi Yang , Zhi Liu

In this paper, we investigate the degree to which fine-tuning in Large Language Models (LLMs) effectively mitigates versus merely conceals undesirable behavior. Through the lens of semi-realistic role-playing exercises designed to elicit…

Computation and Language · Computer Science 2024-07-01 Florin Pop , Judd Rosenblatt , Diogo Schwerz de Lucena , Michael Vaiana

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…

Computation and Language · Computer Science 2024-07-12 Changyu Chen , Xiting Wang , Ting-En Lin , Ang Lv , Yuchuan Wu , Xin Gao , Ji-Rong Wen , Rui Yan , Yongbin Li

Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but…

Machine Learning · Computer Science 2025-10-14 James R. Golden

Training AI models is challenging, particularly when crafting behavior instructions. Traditional methods rely on machines (supervised learning) or manual pattern discovery, which results in not interpretable models or time sink. While Large…

Human-Computer Interaction · Computer Science 2025-03-07 Soya Park , J. D. Zamfirescu-Pereira , Chinmay Kulkarni

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…

Computation and Language · Computer Science 2025-09-22 Joonho Ko , Jinheon Baek , Sung Ju Hwang

Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…

Computation and Language · Computer Science 2022-01-31 Pan He , Yuxi Chen , Yan Wang , Yanru Zhang

Repair, an important resource for resolving trouble in human-human conversation, remains underexplored in human-LLM interaction. In this study, we investigate how LLMs engage in the interactive process of repair in multi-turn dialogues…

Computation and Language · Computer Science 2026-04-23 Clara Lachenmaier , Hannah Bultmann , Sina Zarrieß

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

We introduce DRESS, a novel approach for generating stylized large language model (LLM) responses through representation editing. Existing methods like prompting and fine-tuning are either insufficient for complex style adaptation or…

Computation and Language · Computer Science 2025-01-27 Xinyu Ma , Yifeng Xu , Yang Lin , Tianlong Wang , Xu Chu , Xin Gao , Junfeng Zhao , Yasha Wang

This study evaluates the performance of Large Language Models (LLMs) as an Artificial Intelligence-based tutor for a university course. In particular, different advanced techniques are utilized, such as prompt engineering,…

Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others. Understanding these internal mechanisms is critical - not only…

Computation and Language · Computer Science 2025-05-20 Matteo Bortoletto , Constantin Ruhdorfer , Lei Shi , Andreas Bulling

Intrinsic self-correction refers to the phenomenon where a language model refines its own outputs purely through prompting, without external feedback or parameter updates. While this approach improves performance across diverse tasks, its…

Computation and Language · Computer Science 2026-02-12 Yu-Ting Lee , Fu-Chieh Chang , Yu-En Shu , Hui-Ying Shih , Pei-Yuan Wu

Prompt engineering has emerged as a powerful technique for guiding large language models (LLMs) toward desired responses, significantly enhancing their performance across diverse tasks. Beyond their role as static predictors, LLMs…

Machine Learning · Computer Science 2025-03-27 Ryumei Nakada , Wenlong Ji , Tianxi Cai , James Zou , Linjun Zhang