English
Related papers

Related papers: Optimal and efficient text counterfactuals using G…

200 papers

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art…

Machine Learning · Computer Science 2022-05-10 Silvan Mertes , Tobias Huber , Katharina Weitz , Alexander Heimerl , Elisabeth André

Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal these weaknesses,…

Computation and Language · Computer Science 2022-03-31 Bhargavi Paranjape , Matthew Lamm , Ian Tenney

Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demographic information…

Computation and Language · Computer Science 2025-02-12 Matan Avitan , Ryan Cotterell , Yoav Goldberg , Shauli Ravfogel

Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition. Most existing methods generate explanations by…

Machine Learning · Computer Science 2022-07-14 Mohit Bajaj , Lingyang Chu , Zi Yu Xue , Jian Pei , Lanjun Wang , Peter Cho-Ho Lam , Yong Zhang

LLMs can be unpredictable, as even slight alterations to the prompt can cause the output to change in unexpected ways. Thus, the ability of models to accurately explain their behavior is critical, especially in high-stakes settings. One…

Computation and Language · Computer Science 2025-11-26 Marvin Limpijankit , Yanda Chen , Melanie Subbiah , Nicholas Deas , Kathleen McKeown

Counterfactual explanations are one of the prominent eXplainable Artificial Intelligence (XAI) techniques, and suggest changes to input data that could alter predictions, leading to more favourable outcomes. Existing counterfactual methods…

Artificial Intelligence · Computer Science 2025-05-22 Andrei Buliga , Chiara Di Francescomarino , Chiara Ghidini , Marco Montali , Massimiliano Ronzani

In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental…

Machine Learning · Computer Science 2019-07-09 Shusen Liu , Bhavya Kailkhura , Donald Loveland , Yong Han

One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges…

Machine Learning · Computer Science 2024-09-12 Pirmin Lemberger , Antoine Saillenfest

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be…

Computation and Language · Computer Science 2023-05-29 Marcos Treviso , Alexis Ross , Nuno M. Guerreiro , André F. T. Martins

Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions…

Machine Learning · Computer Science 2025-01-16 Andreas Abildtrup Hansen , Paraskevas Pegios , Anna Calissano , Aasa Feragen

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the…

Machine Learning · Computer Science 2022-10-04 Kevin Xia , Yushu Pan , Elias Bareinboim

Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery -- e.g., model ablations or…

Computation and Language · Computer Science 2025-03-07 Shauli Ravfogel , Anej Svete , Vésteinn Snæbjarnarson , Ryan Cotterell

Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a…

Machine Learning · Computer Science 2020-07-21 Lakshya Jain , Varun Chandrasekaran , Uyeong Jang , Wilson Wu , Andrew Lee , Andy Yan , Steven Chen , Somesh Jha , Sanjit A. Seshia

Counterfactual explanations have emerged as a powerful tool to unveil the opaque decision-making processes of graph neural networks (GNNs). However, existing techniques primarily focus on edge modifications, often overlooking the crucial…

Machine Learning · Computer Science 2025-02-17 Flavio Giorgi , Fabrizio Silvestri , Gabriele Tolomei

The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. Current counterfactual (CF) generation methods require…

Computation and Language · Computer Science 2025-12-11 Van Bach Nguyen , Christin Seifert , Jörg Schlötterer

One of the prominent methods for explaining the decision of a machine-learning classifier is by a counterfactual example. Most current algorithms for generating such examples in the textual domain are based on generative language models.…

Machine Learning · Computer Science 2023-12-19 Daniel Gilo , Shaul Markovitch

Counterfactual examples have emerged as an effective approach to produce simple and understandable post-hoc explanations. In the context of graph classification, previous work has focused on generating counterfactual explanations by…

Machine Learning · Computer Science 2023-07-28 Carlo Abrate , Giulia Preti , Francesco Bonchi

Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we…

Machine Learning · Computer Science 2026-02-09 Yu Zhang , Sean Bin Yang , Arijit Khan , Cuneyt Gurcan Akcora

We study the problem of generating counterfactual text for a classifier as a means for understanding and debugging classification. Given a textual input and a classification model, we aim to minimally alter the text to change the model's…

Computation and Language · Computer Science 2021-10-25 Quintin Pope , Xiaoli Z. Fern