English
Related papers

Related papers: Breaking the Mirror: Activation-Based Mitigation o…

200 papers

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…

Computation and Language · Computer Science 2023-12-08 Ole Jorgensen , Dylan Cope , Nandi Schoots , Murray Shanahan

Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the impact of this framing bias on LLM-based evaluation, where…

Computation and Language · Computer Science 2026-01-21 Yerin Hwang , Dongryeol Lee , Taegwan Kang , Minwoo Lee , Kyomin Jung

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

Computation and Language · Computer Science 2025-07-15 Rongyi Zhu , Yuhui Wang , Tanqiu Jiang , Jiacheng Liang , Ting Wang

As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their users is essential for enhancing…

Human-Computer Interaction · Computer Science 2025-05-15 Jessica Y. Bo , Tianyu Xu , Ishan Chatterjee , Katrina Passarella-Ward , Achin Kulshrestha , D Shin

Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison…

Computation and Language · Computer Science 2026-04-14 Ziwen Xu , Chenyan Wu , Hengyu Sun , Haiwen Hong , Mengru Wang , Yunzhi Yao , Longtao Huang , Hui Xue , Shumin Deng , Zhixuan Chu , Huajun Chen , Ningyu Zhang

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

Computation and Language · Computer Science 2025-04-21 Hawon Jeong , ChaeHun Park , Jimin Hong , Hojoon Lee , Jaegul Choo

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

Cryptography and Security · Computer Science 2026-03-26 Yuxiao Li , Alina Fastowski , Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci

Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is…

Computation and Language · Computer Science 2025-10-28 Xiaoyan Zhao , Ming Yan , Yilun Qiu , Haoting Ni , Yang Zhang , Fuli Feng , Hong Cheng , Tat-Seng Chua

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit $\textbf{modality preference}$, a tendency to favor one modality over…

Computation and Language · Computer Science 2026-02-05 Yu Zhang , Jinlong Ma , Yongshuai Hou , Xuefeng Bai , Kehai Chen , Yang Xiang , Jun Yu , Min Zhang

Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raises a critical fairness concern: systematic bias in tool…

Artificial Intelligence · Computer Science 2026-03-12 Thierry Blankenstein , Jialin Yu , Zixuan Li , Vassilis Plachouras , Sunando Sengupta , Philip Torr , Yarin Gal , Alasdair Paren , Adel Bibi

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs.…

Computation and Language · Computer Science 2025-09-15 Peifeng Wang , Austin Xu , Yilun Zhou , Caiming Xiong , Shafiq Joty

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

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests…

Computation and Language · Computer Science 2025-12-09 Yen-Shan Chen , Jing Jin , Peng-Ting Kuo , Chao-Wei Huang , Yun-Nung Chen

Activation-based steering can personalize large language models at inference time, but its effects in educational settings remain unclear. We study persona vectors for seven character traits in short-answer generation and automated scoring…

Computation and Language · Computer Science 2026-04-09 Yongchao Wu , Aron Henriksson

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

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

LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for…

Machine Learning · Computer Science 2026-05-12 Khurram Yamin , Jingjing Tang , Eric Horvitz , Bryan Wilder