English
Related papers

Related papers: On the (In)fidelity and Sensitivity for Explanatio…

200 papers

Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these…

Machine Learning · Computer Science 2025-01-16 Christopher Burger , Charles Walter

Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text modality and show that the conclusions made for image do not…

Machine Learning · Computer Science 2021-06-15 Narine Kokhlikyan , Vivek Miglani , Bilal Alsallakh , Miguel Martin , Orion Reblitz-Richardson

Robust explanations of machine learning models are critical to establish human trust in the models. Due to limited cognition capability, most humans can only interpret the top few salient features. It is critical to make top salient…

Machine Learning · Computer Science 2023-07-11 Chao Chen , Chenghua Guo , Guixiang Ma , Ming Zeng , Xi Zhang , Sihong Xie

We present a new multi-objective optimization approach for synthesizing interpretations that "explain" the behavior of black-box machine learning models. Constructing human-understandable interpretations for black-box models often requires…

Machine Learning · Computer Science 2021-08-18 Hazem Torfah , Shetal Shah , Supratik Chakraborty , S. Akshay , Sanjit A. Seshia

Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions. We propose a novel measure of individual fairness,…

Artificial Intelligence · Computer Science 2020-09-30 Krystal Maughan , Joseph P. Near

Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabilistic sufficient…

Machine Learning · Computer Science 2021-05-24 Eric Wang , Pasha Khosravi , Guy Van den Broeck

With the dramatic advances in deep learning technology, machine learning research is focusing on improving the interpretability of model predictions as well as prediction performance in both basic and applied research. While deep learning…

Machine Learning · Computer Science 2024-01-24 Shunsuke Kitada

Causal inference relies on the untestable assumption of no unmeasured confounding. Sensitivity analysis can be used to quantify the impact of unmeasured confounding on causal estimates. Among sensitivity analysis methods proposed in the…

Methodology · Statistics 2026-03-12 Yushu Zou , Liangyuan Hu , Amanda Ricciuto , Mark Deneau , Kuan Liu

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Computation and Language · Computer Science 2025-05-21 Katie Matton , Robert Osazuwa Ness , John Guttag , Emre Kıcıman

We propose a novel method for explaining the predictions of any classifier. In our approach, local explanations are expected to explain both the outcome of a prediction and how that prediction would change if 'things had been different'.…

Artificial Intelligence · Computer Science 2019-11-26 Adam White , Artur d'Avila Garcez

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Computation and Language · Computer Science 2023-12-11 Simon Lermen , Ondřej Kvapil

In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…

Machine Learning · Statistics 2020-08-18 Collin Burns , Jesse Thomason , Wesley Tansey

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

Likelihood-free Bayesian inference algorithms are popular methods for calibrating the parameters of complex, stochastic models, required when the likelihood of the observed data is intractable. These algorithms characteristically rely…

Computation · Statistics 2021-12-23 Thomas P Prescott , David J Warne , Ruth E Baker

Causal inference, especially in observational studies, relies on untestable assumptions about the true data-generating process. Sensitivity analysis helps us determine how robust our conclusions are when we alter these underlying…

Machine Learning · Computer Science 2026-05-11 Nikita Dhawan , Daniel Shen , Leonardo Cotta , Chris J. Maddison

Interpretable machine learning models offer understandable reasoning behind their decision-making process, though they may not always match the performance of their black-box counterparts. This trade-off between interpretability and model…

Artificial Intelligence · Computer Science 2025-03-12 Pranjal Atrey , Michael P. Brundage , Min Wu , Sanghamitra Dutta

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic)…

Machine Learning · Computer Science 2024-06-06 Amit Dhurandhar , Swagatam Haldar , Dennis Wei , Karthikeyan Natesan Ramamurthy

In recent years, explainable machine learning methods have been very successful. Despite their success, most explainable machine learning methods are applied to black-box models without any domain knowledge. By incorporating domain…

Machine Learning · Computer Science 2023-09-26 Dangxing Chen

Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such…

Computation and Language · Computer Science 2025-12-09 Dibyanayan Bandyopadhyay , Soham Bhattacharjee , Mohammed Hasanuzzaman , Asif Ekbal

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

Machine Learning · Computer Science 2022-07-08 Gregory Scafarto , Nicolas Posocco , Antoine Bonnefoy