English
Related papers

Related papers: Logic Traps in Evaluating Attribution Scores

200 papers

We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vulnerable to…

Machine Learning · Computer Science 2024-04-10 Miguel Lerma , Mirtha Lucas

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

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

Learning and logic are distinct and remarkable approaches to prediction. Machine learning has experienced a surge in popularity because it is robust to noise and achieves high performance; however, ML experiences many issues with knowledge…

Artificial Intelligence · Computer Science 2018-07-16 Jeffrey Cheng

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

Machine Learning · Computer Science 2020-10-20 Yiding Hao

In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…

Artificial Intelligence · Computer Science 2022-02-09 Dominique Mercier , Jwalin Bhatt , Andreas Dengel , Sheraz Ahmed

Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations. In this work, we explore evidence attribution for fact-checking explanation generation. We introduce a novel…

Computation and Language · Computer Science 2025-02-12 Rui Xing , Timothy Baldwin , Jey Han Lau

My research explores integrating deep learning and logic programming to set the basis for a new generation of AI systems. By combining neural networks with Inductive Logic Programming (ILP), the goal is to construct systems that make…

Logic in Computer Science · Computer Science 2025-02-14 Talissa Dreossi

As large language models (LLMs) become increasingly powerful, traditional evaluation metrics tend to saturate, making it challenging to distinguish between models. We propose a general method to transform existing LLM evaluations into a…

Computation and Language · Computer Science 2025-05-20 William F. Bradley

This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences. We introduce the Alignment Score, a semantic-level metric that…

Artificial Intelligence · Computer Science 2026-04-22 Boxuan Wang , Zhuoyun Li , Xinmiao Huang , Xiaowei Huang , Yi Dong

Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most…

Machine Learning · Computer Science 2020-11-12 Gabriel Erion , Joseph D. Janizek , Pascal Sturmfels , Scott Lundberg , Su-In Lee

Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory aspects like efficiency, hallucination, and adaptivity. The most straightforward method for…

Artificial Intelligence · Computer Science 2026-05-26 Wonjoong Kim , Sangwu Park , Yeonjun In , Sein Kim , Dongha Lee , Chanyoung Park

Large Language Models (LLMs) are increasingly used to evaluate information retrieval (IR) systems, generating relevance judgments traditionally made by human assessors. Recent empirical studies suggest that LLM-based evaluations often align…

Information Retrieval · Computer Science 2026-01-21 Laura Dietz , Oleg Zendel , Peter Bailey , Charles Clarke , Ellese Cotterill , Jeff Dalton , Faegheh Hasibi , Mark Sanderson , Nick Craswell

Studies have underscored how, regardless of the recent breakthrough and swift advances in AI research, even state-of-the-art Large Language models (LLMs) continue to struggle when performing logical and mathematical reasoning. The results…

Artificial Intelligence · Computer Science 2024-12-20 Federico Castagna , Isabel Sassoon , Simon Parsons

Deep learning models continuously break new records across different NLP tasks. At the same time, their success exposes weaknesses of model evaluation. Here, we compile several key pitfalls of evaluation of sentence embeddings, a currently…

Computation and Language · Computer Science 2019-06-05 Steffen Eger , Andreas Rücklé , Iryna Gurevych

In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability. This is evidenced by a high incidence of false positives-solutions that reach the…

Computation and Language · Computer Science 2026-04-20 Youliang Yuan , Qiuyang Mang , Jingbang Chen , Hong Wan , Xiaoyuan Liu , Junjielong Xu , Jen-tse Huang , Wenxuan Wang , Wenxiang Jiao , Pinjia He

Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these…

Computer Vision and Pattern Recognition · Computer Science 2022-07-25 Giang Nguyen , Daeyoung Kim , Anh Nguyen

As machine learning and algorithmic decision making systems are increasingly being leveraged in high-stakes human-in-the-loop settings, there is a pressing need to understand the rationale of their predictions. Researchers have responded to…

Machine Learning · Computer Science 2020-12-07 Jonathan Dinu , Jeffrey Bigham , J. Zico Kolter

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the…

Machine Learning · Computer Science 2022-11-10 Pepa Atanasova

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

‹ Prev 1 3 4 5 6 7 10 Next ›