English
Related papers

Related papers: Sparsity-Guided Holistic Explanation for LLMs with…

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

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation…

Computation and Language · Computer Science 2025-01-10 Melkamu Mersha , Mingiziem Bitewa , Tsion Abay , Jugal Kalita

Explainability for Large Language Models (LLMs) is a critical yet challenging aspect of natural language processing. As LLMs are increasingly integral to diverse applications, their "black-box" nature sparks significant concerns regarding…

Computation and Language · Computer Science 2024-02-23 Haoyan Luo , Lucia Specia

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

We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with…

Computation and Language · Computer Science 2024-07-08 Chung-En Sun , Tuomas Oikarinen , Tsui-Wei Weng

Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language…

Computation and Language · Computer Science 2024-08-26 Mengya Hu , Rui Xu , Deren Lei , Yaxi Li , Mingyu Wang , Emily Ching , Eslam Kamal , Alex Deng

Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoencoders (SAEs) were developed to extract interpretable features…

Machine Learning · Computer Science 2026-01-06 Xiangchen Song , Jiaqi Sun , Zijian Li , Yujia Zheng , Kun Zhang

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance…

Computation and Language · Computer Science 2026-02-02 Alhassan Abdelhalim , Janick Edinger , Sören Laue , Michaela Regneri

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

Recent large vision-language models (LVLMs) have advanced capabilities in visual question answering (VQA). However, interpreting where LVLMs direct their visual attention remains a significant challenge, yet is essential for understanding…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Guanxi Shen

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-17 Akrit Mudvari , Yuang Jiang , Leandros Tassiulas

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

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

We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional black-box LLMs that rely on limited post-hoc interpretations,…

Computation and Language · Computer Science 2025-09-09 Chung-En Sun , Tuomas Oikarinen , Berk Ustun , Tsui-Wei Weng

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Machine Learning · Computer Science 2025-09-30 Yifan Luo , Zhennan Zhou , Bin Dong

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

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

Interpretability remains a key challenge for deploying large language models (LLMs) in clinical settings such as Alzheimer's disease progression diagnosis, where early and trustworthy predictions are essential. Existing attribution methods…

The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and sparsity. Contextual sparsity, where the sparsity pattern is input-dependent, is crucial…

Concept Bottleneck Models (CBMs) have been proposed as a compromise between white-box and black-box models, aiming to achieve interpretability without sacrificing accuracy. The standard training procedure for CBMs is to predefine a…

Machine Learning · Computer Science 2025-12-05 Jean Feng , Avni Kothari , Luke Zier , Chandan Singh , Yan Shuo Tan