English
Related papers

Related papers: Explanation Regeneration via Information Bottlenec…

200 papers

Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose and costly to…

Computation and Language · Computer Science 2026-02-17 Ali Zahedzadeh , Behnam Bahrak

The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required…

Machine Learning · Statistics 2017-11-15 Qianqian Yang , Pablo Piantanida , Deniz Gündüz

Explanation generation frameworks aim to make AI systems' decisions transparent and understandable to human users. However, generating explanations in uncertain environments characterized by incomplete information and probabilistic models…

Artificial Intelligence · Computer Science 2025-09-04 Stylianos Loukas Vasileiou , William Yeoh , Alessandro Previti , Tran Cao Son

Explainable Artificial Intelligence (XAI) has become critical in enhancing the transparency and trustworthiness of AI systems, especially as these systems are increasingly deployed in high-stakes domains such as healthcare and finance.…

Symbolic Computation · Computer Science 2024-08-13 Shengxin Hong , Xiuyi Fan

Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider…

Computation and Language · Computer Science 2025-10-14 Yihang Wang , Xu Huang , Bowen Tian , Yueyang Su , Lei Yu , Huaming Liao , Yixing Fan , Jiafeng Guo , Xueqi Cheng

Maintaining efficient semantic representations of the environment is a major challenge both for humans and for machines. While human languages represent useful solutions to this problem, it is not yet clear what computational principle…

Computation and Language · Computer Science 2018-08-13 Noga Zaslavsky , Charles Kemp , Terry Regier , Naftali Tishby

Although deep neural networks have been immensely successful, there is no comprehensive theoretical understanding of how they work or are structured. As a result, deep networks are often seen as black boxes with unclear interpretations and…

Machine Learning · Computer Science 2022-02-22 Ravid Shwartz-Ziv

This paper presents a method for the automatic extraction of subgrammars to control and speeding-up natural language generation NLG. The method is based on explanation-based learning (EBL). The main advantage for the proposed new method for…

cmp-lg · Computer Science 2007-05-23 Guenter Neumann

Natural language free-text explanation generation is an efficient approach to train explainable language processing models for commonsense-knowledge-requiring tasks. The most predominant form of these models is the explain-then-predict…

Computation and Language · Computer Science 2021-10-06 Myeongjun Jang , Thomas Lukasiewicz

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we…

Computation and Language · Computer Science 2025-10-10 Md Kowsher , Nusrat Jahan Prottasha , Shiyun Xu , Shetu Mohanto , Ozlem Garibay , Niloofar Yousefi , Chen Chen

Information bottleneck (IB) is a paradigm to extract information in one target random variable from another relevant random variable, which has aroused great interest due to its potential to explain deep neural networks in terms of…

Information Theory · Computer Science 2023-08-23 Lingyi Chen , Shitong Wu , Wenhao Ye , Huihui Wu , Hao Wu , Wenyi Zhang , Bo Bai , Yining Sun

The information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of the target task. In…

Computation and Language · Computer Science 2023-02-13 Nhung T. H. Nguyen , Makoto Miwa , Sophia Ananiadou

The Information Bottleneck (IB) principle has emerged as a promising approach for enhancing the generalization, robustness, and interpretability of deep neural networks, demonstrating efficacy across image segmentation, document clustering,…

Information Theory · Computer Science 2025-04-18 Hanzhe Yang , Youlong Wu , Dingzhu Wen , Yong Zhou , Yuanming Shi

The fruits of science are relationships made comprehensible, often by way of approximation. While deep learning is an extremely powerful way to find relationships in data, its use in science has been hindered by the difficulty of…

Machine Learning · Computer Science 2022-04-18 Kieran A. Murphy , Dani S. Bassett

Large Language Models excel in tasks like natural language understanding and text generation. Prompt engineering plays a critical role in leveraging LLM effectively. However, LLMs black-box nature hinders its interpretability and effective…

Computation and Language · Computer Science 2024-10-31 Ximing Dong , Shaowei Wang , Dayi Lin , Gopi Krishnan Rajbahadur , Boquan Zhou , Shichao Liu , Ahmed E. Hassan

The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably,…

Machine Learning · Computer Science 2022-02-15 Stephan Sloth Lorenzen , Christian Igel , Mads Nielsen

Extracting relevant information from data is crucial for all forms of learning. The information bottleneck (IB) method formalizes this, offering a mathematically precise and conceptually appealing framework for understanding learning…

Machine Learning · Computer Science 2021-10-27 Vudtiwat Ngampruetikorn , David J. Schwab

As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax. This view rests upon a hypothesis that has not yet been empirically…

Computation and Language · Computer Science 2021-09-13 Nikolay Malkin , Sameera Lanka , Pranav Goel , Nebojsa Jojic

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

Machine Learning · Computer Science 2024-05-24 Ling Han , Hao Huang , Dustin Scheinost , Mary-Anne Hartley , María Rodríguez Martínez

The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate…

Artificial Intelligence · Computer Science 2024-10-23 Germán Vidal