English
Related papers

Related papers: SPEX: Scaling Feature Interaction Explanations for…

200 papers

Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…

Computation and Language · Computer Science 2024-06-12 Jifeng Song , Kai Huang , Xiangyu Yin , Boyuan Yang , Wei Gao

Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making…

Machine Learning · Computer Science 2025-11-26 Shuyi Zhang , Wei Shi , Sihang Li , Jiayi Liao , Hengxing Cai , Xiang Wang

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

Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood. Existing interpretability research has primarily…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Jiawei Liang , Ruoyu Chen , Xianghao Jiao , Siyuan Liang , Shiming Liu , Qunli Zhang , Zheng Hu , Xiaochun Cao

Multi-turn interactions between large language models (LLMs) and users naturally include implicit feedback signals. If an LLM responds in an unexpected way to an instruction, the user is likely to signal it by rephrasing the request,…

Computation and Language · Computer Science 2025-05-22 Zizhao Chen , Mustafa Omer Gul , Yiwei Chen , Gloria Geng , Anne Wu , Yoav Artzi

Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often…

Computation and Language · Computer Science 2025-08-08 Furui Cheng , Vilém Zouhar , Robin Shing Moon Chan , Daniel Fürst , Hendrik Strobelt , Mennatallah El-Assady

Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience…

Artificial Intelligence · Computer Science 2025-09-24 Xingkun Yin , Kaibin Huang , Dong In Kim , Hongyang Du

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

Full-Duplex Speech-to-Speech Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling real-time spoken dialogue systems. However, benchmarking and modeling these models remains a fundamental challenge.…

Computation and Language · Computer Science 2025-09-29 Yuan Ge , Saihan Chen , Jingqi Xiao , Xiaoqian Liu , Tong Xiao , Yan Xiang , Zhengtao Yu , Jingbo Zhu

A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…

Machine Learning · Computer Science 2024-11-08 Jacob Dunefsky , Philippe Chlenski , Neel Nanda

While Large language models (LLMs) have advanced natural language processing tasks, their growing computational and memory demands make deployment on resource-constrained devices like mobile phones increasingly challenging. In this paper,…

Machine Learning · Computer Science 2025-02-13 Yiping Wang , Hanxian Huang , Yifang Chen , Jishen Zhao , Simon Shaolei Du , Yuandong Tian

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

Identifying relevant text spans is important for several downstream tasks in NLP, as it contributes to model explainability. While most span identification approaches rely on relatively smaller pre-trained language models like BERT, a few…

Computation and Language · Computer Science 2026-01-05 Alphaeus Dmonte , Roland Oruche , Tharindu Ranasinghe , Marcos Zampieri , Prasad Calyam

It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Huadong Tang , Youpeng Zhao , Yan Huang , Min Xu , Jun Wang , Qiang Wu

This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions. We examine two classification tasks: (i) a binary classification problem focused on…

Transformer-based Large Language Models (LLMs) are pioneering advances in many natural language processing tasks, however, their exceptional capabilities are restricted within the preset context window of Transformer. Position Embedding…

Computation and Language · Computer Science 2024-03-26 Guanzheng Chen , Xin Li , Zaiqiao Meng , Shangsong Liang , Lidong Bing

Feature selection has been widely used to alleviate compute requirements during training, elucidate model interpretability, and improve model generalizability. We propose SLM -- Sparse Learnable Masks -- a canonical approach for end-to-end…

Machine Learning · Computer Science 2023-04-07 Yihe Dong , Sercan O. Arik

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…

Computation and Language · Computer Science 2025-04-18 Linda He , Jue Wang , Maurice Weber , Shang Zhu , Ben Athiwaratkun , Ce Zhang

SHAP is a popular approach to explain black-box models by revealing the importance of individual features. As it ignores feature interactions, SHAP explanations can be confusing up to misleading. NSHAP, on the other hand, reports the…

Machine Learning · Computer Science 2024-04-22 Sascha Xu , Joscha Cüppers , Jilles Vreeken