English
Related papers

Related papers: RepIt: Steering Language Models with Concept-Speci…

200 papers

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…

Computation and Language · Computer Science 2025-08-12 Hannah Cyberey , David Evans

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Artificial Intelligence · Computer Science 2025-09-25 Huizhen Shu , Xuying Li , Zhuo Li

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Artificial Intelligence · Computer Science 2026-03-17 Rishab Alagharu , Ishneet Sukhvinder Singh , Shaibi Shamsudeen , Zhen Wu , Ashwinee Panda

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Cryptography and Security · Computer Science 2026-01-13 Xin Wang , Yunhao Chen , Juncheng Li , Yixu Wang , Yang Yao , Tianle Gu , Jie Li , Yan Teng , Yingchun Wang , Xia Hu

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

Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks…

Sound · Computer Science 2026-05-08 Weilin Lin , Jianze Li , Hui Xiong , Li Liu

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

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

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…

Machine Learning · Computer Science 2026-04-10 Stephen Cheng , Sarah Wiegreffe , Dinesh Manocha

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

Cryptography and Security · Computer Science 2025-09-22 Weixiang Zhao , Jiahe Guo , Yulin Hu , Yang Deng , An Zhang , Xingyu Sui , Xinyang Han , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks range from localized physical patches to imperceptible global perturbations. Existing defense…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Xiaoxu Peng , Dong Zhou , Jianwen Zhang , Guanghui Sun , Anh Tu Ngo , Anupam Chattopadhyay

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…

Computation and Language · Computer Science 2026-02-23 Joschka Braun

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

Referring Expression Segmentation (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions, supporting critical applications such as human-robot interaction and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Yihao Wang , Jusheng Zhang , Ziyi Tang , Keze Wang , Meng Yang

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper…

Artificial Intelligence · Computer Science 2026-05-12 Jialin Wu , Wei Shi , Han Shen , Peigui Qi , Kunsheng Tang , Zhicong Huang , Binghao Wang , Zhou Yang

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…

Computation and Language · Computer Science 2024-11-05 Jason Cai , Hang Su , Monica Sunkara , Igor Shalyminov , Saab Mansour

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

Recent advancements in large language models (LLMs) have resulted in increasingly anthropomorphic language concerning the ability of LLMs to reason. Whether reasoning in LLMs should be understood to be inherently different is, however,…

Machine Learning · Computer Science 2025-07-28 Bertram Højer , Oliver Jarvis , Stefan Heinrich

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah