English
Related papers

Related papers: SCAN: Sparse Circuit Anchor Interpretable Neuron f…

200 papers

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

Large Language Models (LLMs) have achieved unprecedented breakthroughs in various natural language processing domains. However, the enigmatic ``black-box'' nature of LLMs remains a significant challenge for interpretability, hampering…

Computation and Language · Computer Science 2023-12-27 Zhen Tan , Tianlong Chen , Zhenyu Zhang , Huan Liu

Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. To this end, many knowledge editing…

Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose $\textit{Specify ANd Edit}$ (SANE), a zero-shot inference pipeline for diffusion-based editing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Ekaterina Iakovleva , Fabio Pizzati , Philip Torr , Stéphane Lathuilière

Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model's knowledge remains…

Computation and Language · Computer Science 2026-02-11 Junjie Ye , Yuming Yang , Yang Nan , Shuo Li , Qi Zhang , Tao Gui , Xuanjing Huang , Peng Wang , Zhongchao Shi , Jianping Fan

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Machine Learning · Computer Science 2026-05-28 Li Lei , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…

Computation and Language · Computer Science 2024-05-14 Yuchen Cai , Ding Cao , Rongxi Guo , Yaqin Wen , Guiquan Liu , Enhong Chen

In existing semantic communication systems for image transmission, some images are generally reconstructed with considerably low quality. As a result, the reliable transmission of each image cannot be guaranteed, bringing significant…

Signal Processing · Electrical Eng. & Systems 2023-06-28 Guangyi Zhang , Qiyu Hu , Yunlong Cai , Guanding Yu

Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from polysemanticity, leading to limited knowledge expression and…

Computation and Language · Computer Science 2025-02-28 Yuheng Chen , Pengfei Cao , Kang Liu , Jun Zhao

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra…

Computation and Language · Computer Science 2024-02-20 Zihao Lin , Mohammad Beigi , Hongxuan Li , Yufan Zhou , Yuxiang Zhang , Qifan Wang , Wenpeng Yin , Lifu Huang

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of…

Robotics · Computer Science 2019-03-07 Mehdi Hosseinzadeh , Kejie Li , Yasir Latif , Ian Reid

With the remarkable success of large language models (LLMs) in natural language understanding and generation, multimodal large language models (MLLMs) have rapidly advanced in their ability to process data across multiple modalities. While…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jingrui Zhang , Feng Liang , Yong Zhang , Wei Wang , Runhao Zeng , Xiping Hu

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Computation and Language · Computer Science 2024-08-09 Tyler Lizzo , Larry Heck

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

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners…

Computation and Language · Computer Science 2025-02-12 Guangyao Dou , Zheyuan Liu , Qing Lyu , Kaize Ding , Eric Wong

As AI models achieve remarkable capabilities across diverse domains, understanding what representations they learn and how they encode concepts has become increasingly important for both scientific progress and trustworthy deployment.…

Machine Learning · Computer Science 2026-05-05 Yiming Tang , Harshvardhan Saini , Zhaoqian Yao , Zheng Lin , Yizhen Liao , Jingyi Cui , Yisen Wang , Mengnan Du , Dianbo Liu

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Computation and Language · Computer Science 2024-12-19 Weiyu Huang , Yuezhou Hu , Guohao Jian , Jun Zhu , Jianfei Chen

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters…

Machine Learning · Computer Science 2026-05-05 Fatema Siddika , Md Anwar Hossen , Tanwi Mallick , Ali Jannesari

Large language models (LLMs) possess vast knowledge acquired from extensive training corpora, but they often cannot remove specific pieces of information when needed, which makes it hard to handle privacy, bias mitigation, and knowledge…

Machine Learning · Computer Science 2025-12-09 Yezi Liu , Hanning Chen , Wenjun Huang , Yang Ni , Mohsen Imani