English
Related papers

Related papers: Interpretable Safety Alignment via SAE-Constructed…

200 papers

Real-world autonomous driving must adhere to complex human social rules that extend beyond legally codified traffic regulations. Many of these semantic constraints, such as yielding to emergency vehicles, complying with traffic officers'…

Robotics · Computer Science 2026-01-06 Qian Cheng , Weitao Zhou , Cheng Jing , Nanshan Deng , Junze Wen , Zhaoyang Liu , Kun Jiang , Diange Yang

Reasoning-capable LLMs have achieved major breakthroughs in solving complex problems, but recent work shows that acquiring and deploying strong reasoning can introduce significant safety risks. A common mitigation is to apply a secondary…

Artificial Intelligence · Computer Science 2026-02-03 Yihao Xue , Baharan Mirzasoleiman

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Artificial Intelligence · Computer Science 2025-02-04 Guanlin Li , Kangjie Chen , Shangwei Guo , Jie Zhang , Han Qiu , Chao Zhang , Guoyin Wang , Tianwei Zhang , Jiwei Li

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety alignment, e.g., by greatly increasing susceptibility to…

Machine Learning · Computer Science 2026-01-16 Jiawen Zhang , Yangfan Hu , Kejia Chen , Lipeng He , Jiachen Ma , Jian Lou , Dan Li , Jian Liu , Xiaohu Yang , Ruoxi Jia

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Computation and Language · Computer Science 2025-04-04 Nikhil Verma , Manasa Bharadwaj

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Machine Learning · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…

Machine Learning · Computer Science 2025-02-25 Subhash Kantamneni , Joshua Engels , Senthooran Rajamanoharan , Max Tegmark , Neel Nanda

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Computation and Language · Computer Science 2025-06-10 Jiaming Li , Haoran Ye , Yukun Chen , Xinyue Li , Lei Zhang , Hamid Alinejad-Rokny , Jimmy Chih-Hsien Peng , Min Yang

With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more challenging and their alignment less stable, particularly…

Machine Learning · Computer Science 2025-06-18 Hantao Lou , Changye Li , Jiaming Ji , Yaodong Yang

End-to-end autonomous driving systems excel in common scenarios but struggle with safety-critical long-tail cases. Vision-Language-Action (VLA) models are promising due to their strong reasoning capabilities. However, most VLA-based…

Robotics · Computer Science 2026-05-20 Kefei Tian , Yuansheng Lian , Kai Yang , Xiangdong Chen , Shen Li

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Machine Learning · Computer Science 2026-02-09 John Yan , Michael Yu , Yuqi Sun , Alexander Duffy , Tyler Marques , Matthew Lyle Olson

Safety alignment is essential for building trustworthy artificial intelligence, yet it remains challenging to enhance model safety without degrading general performance. Current approaches require computationally expensive searches for the…

Computation and Language · Computer Science 2025-10-13 Yutao Mou , Xiaoling Zhou , Yuxiao Luo , Shikun Zhang , Wei Ye

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to…

Computation and Language · Computer Science 2025-06-04 Weikai Lu , Hao Peng , Huiping Zhuang , Cen Chen , Ziqian Zeng

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Machine Learning · Computer Science 2025-08-14 Charles O'Neill , Mudith Jayasekara , Max Kirkby

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Machine Learning · Computer Science 2025-11-04 Samaksh Bhargav , Zining Zhu