English
Related papers

Related papers: Constructing Interpretable Features from Compositi…

200 papers

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine,…

Machine Learning · Computer Science 2026-05-05 Hongxi Mao , Wei Zhou , Mengting Jia , Tao Fang , Huan Gao , Bin Zhang , Shangyang Li

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies. To interpret the decision process of a trained classifier, existing techniques typically…

Image and Video Processing · Electrical Eng. & Systems 2021-06-29 Zixuan Liu , Ehsan Adeli , Kilian M. Pohl , Qingyu Zhao

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

Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods…

Machine Learning · Computer Science 2024-02-20 Moritz Lange , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Machine Learning · Computer Science 2025-11-13 Ege Erdogan , Ana Lucic

Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We systematically analyze both encoder and decoder based LLMs…

Machine Learning · Computer Science 2026-04-13 Muhammad Umair Haider , Hammad Rizwan , Hassan Sajjad , Peizhong Ju , A. B. Siddique

Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes understanding their internal decision-making challenging. Existing…

Machine Learning · Computer Science 2025-11-27 Matīss Kalnāre , Sofoklis Kitharidis , Thomas Bäck , Niki van Stein

Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with…

Computation and Language · Computer Science 2024-07-31 Yuni Susanti , Michael Färber

The meaning of a natural language utterance is largely determined from its syntax and words. Additionally, there is evidence that humans process an utterance by separating knowledge about the lexicon from syntax knowledge. Theories from…

Computation and Language · Computer Science 2020-02-21 Tristan Thrush

Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the…

Computation and Language · Computer Science 2018-10-23 Mahnaz Koupaee , William Yang Wang

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…

Computation and Language · Computer Science 2024-06-12 Haowen Pan , Yixin Cao , Xiaozhi Wang , Xun Yang , Meng Wang

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation…

Artificial Intelligence · Computer Science 2022-05-20 Antonia Creswell , Murray Shanahan , Irina Higgins

Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to…

Computation and Language · Computer Science 2026-01-28 Yifan Wang , Jichen Zheng , Jingyuan Sun , Yunhao Zhang , Chunyu Ye , Jixing Li , Chengqing Zong , Shaonan Wang

Interpreting the inner workings of neural models is a key step in ensuring the robustness and trustworthiness of the models, but work on neural network interpretability typically faces a trade-off: either the models are too constrained to…

Computation and Language · Computer Science 2020-11-11 Phong Le , Willem Zuidema

Low dimensional nonlinear structure abounds in datasets across computer vision and machine learning. Kernelized matrix factorization techniques have recently been proposed to learn these nonlinear structures for denoising, classification,…

Machine Learning · Computer Science 2021-06-01 Jicong Fan , Chengrun Yang , Madeleine Udell

Large language models (LLMs) often struggle with complex mathematical tasks, prone to "hallucinating" incorrect answers due to their reliance on statistical patterns. This limitation is further amplified in average Small LangSLMs with…

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

Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on post-hoc methods, we present \textbf{MoE-X}, a…

In recent years, multimodal large language models (MLLMs) have significantly advanced, integrating more modalities into diverse applications. However, the lack of explainability remains a major barrier to their use in scenarios requiring…

Computation and Language · Computer Science 2024-10-08 Kaichen Huang , Jiahao Huo , Yibo Yan , Kun Wang , Yutao Yue , Xuming Hu

Word embeddings are a basic building block of modern NLP pipelines. Efforts have been made to learn rich, efficient, and interpretable embeddings for large generic datasets available in the public domain. However, these embeddings have…

Computation and Language · Computer Science 2021-03-23 Rishabh Gupta , Rajesh N Rao