English
Related papers

Related papers: Breaking Bad Tokens: Detoxification of LLMs Using …

200 papers

Large language models (LLMs) demonstrate exceptional performance on tasks requiring complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their…

Computation and Language · Computer Science 2025-09-16 Yi Jing , Zijun Yao , Hongzhu Guo , Lingxu Ran , Xiaozhi Wang , Lei Hou , Juanzi Li

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Computation and Language · Computer Science 2025-06-03 Yuanhe Tian , Mingjie Deng , Guoqing Jin , Yan Song

Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety has received relatively limited attention. Even the latest…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Hao Wang , Yiqun Sun , Pengfei Wei , Lawrence B. Hsieh , Daisuke Kawahara

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires…

Computation and Language · Computer Science 2024-09-11 Joymallya Chakraborty , Wei Xia , Anirban Majumder , Dan Ma , Walid Chaabene , Naveed Janvekar

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs)…

Computation and Language · Computer Science 2026-04-28 Tomer Ashuach , Dana Arad , Aaron Mueller , Martin Tutek , Yonatan Belinkov

Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge,…

Computation and Language · Computer Science 2024-05-21 Tinh Son Luong , Thanh-Thien Le , Linh Ngo Van , Thien Huu Nguyen

Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static classifiers and labor-intensive labeling struggle to keep…

Computation and Language · Computer Science 2026-04-02 Suraj Kath , Sanket Badhe , Preet Shah , Ashwin Sampathkumar , Shivani Gupta

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose generation fluency.…

Computation and Language · Computer Science 2025-10-16 Ming Dong , Jinkui Zhang , Bolong Zheng , Xinhui Tu , Po Hu , Tingting He

Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…

Artificial Intelligence · Computer Science 2026-03-18 Eshwar Reddy M , Sourav Karmakar

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Machine Learning · Computer Science 2025-07-18 Nikita Koriagin , Yaroslav Aksenov , Daniil Laptev , Gleb Gerasimov , Nikita Balagansky , Daniil Gavrilov

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…

Computation and Language · Computer Science 2024-05-29 Mengru Wang , Ningyu Zhang , Ziwen Xu , Zekun Xi , Shumin Deng , Yunzhi Yao , Qishen Zhang , Linyi Yang , Jindong Wang , Huajun Chen

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Sonia Joseph , Praneet Suresh , Ethan Goldfarb , Lorenz Hufe , Yossi Gandelsman , Robert Graham , Danilo Bzdok , Wojciech Samek , Blake Aaron Richards

Language is a deep-rooted means of perpetration of stereotypes and discrimination. Large Language Models (LLMs), now a pervasive technology in our everyday lives, can cause extensive harm when prone to generating toxic responses. The…

Software Engineering · Computer Science 2026-02-06 Simone Corbo , Luca Bancale , Valeria De Gennaro , Livia Lestingi , Vincenzo Scotti , Matteo Camilli

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…

Computation and Language · Computer Science 2026-02-27 Usha Bhalla , Alex Oesterling , Claudio Mayrink Verdun , Himabindu Lakkaraju , Flavio P. Calmon

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using…

Machine Learning · Computer Science 2026-05-15 Bat-Sheva Einbinder , Hen Davidov , Yee Whye Teh , Yarin Gal , Yaniv Romano