English
Related papers

Related papers: Reckoning with the Disagreement Problem: Explanati…

200 papers

Post-hoc explanation methods attempt to make the inner workings of deep neural networks more interpretable. However, since a ground truth is in general lacking, local post-hoc interpretability methods, which assign importance scores to…

Machine Learning · Computer Science 2023-11-27 Lennart Brocki , Neo Christopher Chung

The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either…

Computation and Language · Computer Science 2020-06-25 Hannah Chen , Yangfeng Ji , David Evans

We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's reliance on spurious signals in the training data. Specifically,…

Machine Learning · Computer Science 2022-12-12 Julius Adebayo , Michael Muelly , Hal Abelson , Been Kim

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the…

Machine Learning · Computer Science 2021-06-01 Ramaravind Kommiya Mothilal , Divyat Mahajan , Chenhao Tan , Amit Sharma

Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by…

Computation and Language · Computer Science 2022-03-18 Giuseppe Attanasio , Debora Nozza , Dirk Hovy , Elena Baralis

The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that…

Artificial Intelligence · Computer Science 2026-03-11 Stefano Fioravanti , Francesco Giannini , Paolo Frazzetto , Fabio Zanasi , Pietro Barbiero

For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning…

Machine Learning · Computer Science 2020-10-09 Laura Rieger , Chandan Singh , W. James Murdoch , Bin Yu

Explainability is needed to establish confidence in machine learning results. Some explainable methods take a post hoc approach to explain the weights of machine learning models, others highlight areas of the input contributing to…

Machine Learning · Computer Science 2024-07-15 Paul Whitten , Francis Wolff , Chris Papachristou

Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zubair Faruqui , Rahul Dubey

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Machine Learning · Computer Science 2025-07-28 Minghui Sun , Benjamin A. Goldstein , Matthew M. Engelhard

Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques…

Machine Learning · Computer Science 2025-01-27 RuiZhe Jiang , Haotian Lei

Superposition refers to encoding representations of multiple features within a single neuron, which is common in deep neural networks. This property allows neurons to combine and represent multiple features, enabling the model to capture…

Machine Learning · Computer Science 2025-02-12 Ruidi Chang , Chunyuan Deng , Hanjie Chen

Although a plethora of architectural variants for deep classification has been introduced over time, recent works have found empirical evidence towards similarities in their training process. It has been hypothesized that neural networks…

Machine Learning · Computer Science 2022-07-20 Iuliia Pliushch , Martin Mundt , Nicolas Lupp , Visvanathan Ramesh

We consider the problem of jointly training structured models for extraction from sources whose instances enjoy partial overlap. This has important applications like user-driven ad-hoc information extraction on the web. Such applications…

Artificial Intelligence · Computer Science 2017-07-07 Rahul Gupta , Sunita Sarawagi

Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical…

Machine Learning · Computer Science 2023-08-24 Amr Alkhatib , Henrik Boström , Sofiane Ennadir , Ulf Johansson

With the growing privacy concerns in recommender systems, recommendation unlearning is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as unlearning target. However, attackers can extract…

Information Retrieval · Computer Science 2024-10-25 Chaochao Chen , Yizhao Zhang , Yuyuan Li , Jun Wang , Lianyong Qi , Xiaolong Xu , Xiaolin Zheng , Jianwei Yin

Reliable pattern recognition systems should exhibit consistent behavior across similar inputs, and their explanations should remain stable. However, most Explainable AI evaluations remain instance centric and do not explicitly quantify…

Artificial Intelligence · Computer Science 2026-04-07 Abu Noman Md Sakib , Zhensen Wang , Merjulah Roby , Zijie Zhang

A primary goal of online deliberation platforms is to identify ideas that are broadly agreeable to a community of users through their expressed preferences. Yet, consensus elicitation should ideally extend beyond the specific statements…

Machine Learning · Computer Science 2026-04-24 Carter Blair , Ben Armstrong , Shiri Alouf-Heffetz , Nimrod Talmon , Davide Grossi

The non-humanlike behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon of such faulty behaviours is the generation of inconsistent predictions, which…

Computation and Language · Computer Science 2023-10-25 Myeongjun Erik Jang , Thomas Lukasiewicz

We introduce CLEAR (Contrasting Textual Feedback with Experts and Amateurs for Reasoning), a novel approach to language model reasoning that leverages the strengths of a larger (expert) model and smaller (amateur) model. The expert and…

Computation and Language · Computer Science 2025-04-11 Andrew Rufail , Daniel Kim , Sean O'Brien , Kevin Zhu