English
Related papers

Related papers: On Guaranteed Optimal Robust Explanations for NLP …

200 papers

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…

Machine Learning · Computer Science 2021-06-22 Nathan Dahlin , Krishna Chaitanya Kalagarla , Nikhil Naik , Rahul Jain , Pierluigi Nuzzo

Trustworthiness in artificial intelligence depends not only on what a model decides, but also on how it handles and explains cases in which a reliable decision cannot be made. In critical domains such as healthcare and finance, a reject…

Machine Learning · Computer Science 2026-03-17 Gleilson Pedro Fernandes , Thiago Alves Rocha

Although existing machine reading comprehension models are making rapid progress on many datasets, they are far from robust. In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of…

Computation and Language · Computer Science 2022-07-04 Feiliang Ren , Yongkang Liu , Bochao Li , Shilei Liu , Bingchao Wang , Jiaqi Wang , Chunchao Liu , Qi Ma

Modern language models (LMs) are not robust to out-of-distribution inputs. Machine generated (``optimized'') prompts can be used to modulate LM outputs and induce specific behaviors while appearing completely uninterpretable. In this work,…

Computation and Language · Computer Science 2025-09-04 Rimon Melamed , Lucas H. McCabe , H. Howie Huang

Previous research has demonstrated that natural language explanations provide valuable inductive biases that guide models, thereby improving the generalization ability and data efficiency. In this paper, we undertake a systematic…

Computation and Language · Computer Science 2023-05-26 Wanyun Cui , Xingran Chen

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical…

Computation and Language · Computer Science 2020-06-16 Xisen Jin , Zhongyu Wei , Junyi Du , Xiangyang Xue , Xiang Ren

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN…

Machine Learning · Computer Science 2022-12-20 Tianxiang Zhao , Dongsheng Luo , Xiang Zhang , Suhang Wang

The machine learning literature contains several constructions for prediction intervals that are intuitively reasonable but ultimately ad-hoc in that they do not come with provable performance guarantees. We present methods from the…

Machine Learning · Statistics 2020-02-25 Danijel Kivaranovic , Kory D. Johnson , Hannes Leeb

Despite the recent progress in deep neural networks (DNNs), it remains challenging to explain the predictions made by DNNs. Existing explanation methods for DNNs mainly focus on post-hoc explanations where another explanatory model is…

Machine Learning · Computer Science 2024-01-04 Wei Qian , Chenxu Zhao , Yangyi Li , Fenglong Ma , Chao Zhang , Mengdi Huai

Solving combinatorial optimization problems involve satisfying a set of hard constraints while optimizing some objectives. In this context, exact or approximate methods can be used. While exact methods guarantee the optimal solution, they…

Artificial Intelligence · Computer Science 2024-09-13 Aymen Ben Said , Malek Mouhoub

We propose a novel way to handle out of vocabulary (OOV) words in downstream natural language processing (NLP) tasks. We implement a network that predicts useful embeddings for OOV words based on their morphology and on the context in which…

Computation and Language · Computer Science 2019-03-05 Nicolas Garneau , Jean-Samuel Leboeuf , Luc Lamontagne

Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts, but there has been limited understanding of exactly how these explanations function or why they are effective. This work aims to…

Computation and Language · Computer Science 2023-06-14 Xi Ye , Srinivasan Iyer , Asli Celikyilmaz , Ves Stoyanov , Greg Durrett , Ramakanth Pasunuru

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as supervision to…

Computation and Language · Computer Science 2021-12-08 Sarah Wiegreffe , Ana Marasović

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose…

Computation and Language · Computer Science 2016-10-07 Kim Anh Nguyen , Sabine Schulte im Walde , Ngoc Thang Vu

Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which…

Machine Learning · Statistics 2023-11-06 Sanjeeb Dash , Soumyadip Ghosh , Joao Goncalves , Mark S. Squillante

In recent years numerous methods have been developed to formally verify the robustness of deep neural networks (DNNs). Though the proposed techniques are effective in providing mathematical guarantees about the DNNs behavior, it is not…

Machine Learning · Computer Science 2023-02-01 Debangshu Banerjee , Avaljot Singh , Gagandeep Singh

When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities. If we humans cannot figure out the meaning of those…

Computation and Language · Computer Science 2019-04-11 Shonosuke Ishiwatari , Hiroaki Hayashi , Naoki Yoshinaga , Graham Neubig , Shoetsu Sato , Masashi Toyoda , Masaru Kitsuregawa

We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding. Here understanding is intended as mapping data to an already existing representation which encodes an {\em a priori}…

Disordered Systems and Neural Networks · Physics 2023-12-07 Rongrong Xie , Matteo Marsili

In this paper, we introduce a method for approximating the solution to inference and optimization tasks in uncertain and deterministic reasoning. Such tasks are in general intractable for exact algorithms because of the large number of…

Artificial Intelligence · Computer Science 2012-12-12 David Ephraim Larkin