Related papers: TIGTEC : Token Importance Guided TExt Counterfactu…

The proliferation of fake news, i.e., news intentionally spread for misinformation, poses a threat to individuals and society. Despite various fact-checking websites such as PolitiFact, robust detection techniques are required to deal with…

Reinforcement learning for open-ended text generation is constrained by the lack of verifiable rewards, necessitating reliance on judge models that require either annotated data or powerful closed-source models. Inspired by recent work on…

Topic modeling is pivotal in discerning hidden semantic structures within texts, thereby generating meaningful descriptive keywords. While innovative techniques like BERTopic and Top2Vec have recently emerged in the forefront, they manifest…

Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution…

In this paper, we demonstrate the feasibility of alterfactual explanations for black box image classifiers. Traditional explanation mechanisms from the field of Counterfactual Thinking are a widely-used paradigm for Explainable Artificial…

In this work, we instantiate a novel perturbation-based multi-class explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation). We demonstrate that LIPEx not only locally replicates the probability distributions output…

Scientific expertise often requires recognizing subtle visual differences that remain challenging to articulate even for domain experts. We present a system that leverages generative models to automatically discover and visualize minimal…

The goal of local citation recommendation is to recommend a missing reference from the local citation context and optionally also from the global context. To balance the tradeoff between speed and accuracy of citation recommendation in the…

The increased interest in deep learning applications, and their hard-to-detect biases result in the need to validate and explain complex models. However, current explanation methods are limited as far as both the explanation of the…

Learning-to-Rank (LTR) models trained from implicit feedback (e.g. clicks) suffer from inherent biases. A well-known one is the position bias -- documents in top positions are more likely to receive clicks due in part to their position…

Machine Learning has seen tremendous growth recently, which has led to larger adoption of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP…

Towards better explainability in the field of information retrieval, we present CREDENCE, an interactive tool capable of generating counterfactual explanations for document rankers. Embracing the unique properties of the ranking problem, we…

The importance of the neighborhood for training a local surrogate model to approximate the local decision boundary of a black box classifier has been already highlighted in the literature. Several attempts have been made to construct a…

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors. For instance, changing a single token in the text can…

Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired…

Automatic keyphrase labelling stands for the ability of models to retrieve words or short phrases that adequately describe documents' content. Previous work has put much effort into exploring extractive techniques to address this task;…

Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse. We argue that it is beneficial to provide several alternative explanations rather than a single…

Machine learning models achieve state-of-the-art performance across domains, yet their lack of interpretability limits safe deployment in high-stakes settings. Counterfactual explanations are widely used to provide actionable "what-if"…

We present a new method for generating plausible counterfactual explanations for time series classification problems. The approach performs gradient-based optimization directly in the input space. To enforce plausibility, we integrate…