English
Related papers

Related papers: Logic Traps in Evaluating Attribution Scores

200 papers

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

Machine Learning · Computer Science 2018-10-03 Andrew Slavin Ross

Despite recent advances in modern machine learning algorithms, the opaqueness of their underlying mechanisms continues to be an obstacle in adoption. To instill confidence and trust in artificial intelligence systems, Explainable Artificial…

Machine Learning · Computer Science 2023-03-06 Zheng Zhang , Liangliang Xu , Levent Yilmaz , Bo Liu

Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., whether every claim within the generated responses is fully…

Computation and Language · Computer Science 2024-02-26 Yifei Li , Xiang Yue , Zeyi Liao , Huan Sun

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…

Machine Learning · Computer Science 2022-05-02 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

Human relevance assessment is time-consuming and cognitively intensive, limiting the scalability of Information Retrieval evaluation. This has led to growing interest in using large language models (LLMs) as proxies for human judges.…

Information Retrieval · Computer Science 2026-04-28 Chuting Yu , Hang Li , Guido Zuccon , Joel Mackenzie , Teerapong Leelanupab

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing is often overestimated and…

The ability to conduct logical reasoning is a fundamental aspect of intelligent human behavior, and thus an important problem along the way to human-level artificial intelligence. Traditionally, logic-based symbolic methods from the field…

Artificial Intelligence · Computer Science 2021-01-11 Patrick Hohenecker , Thomas Lukasiewicz

Reward hacking, where a reasoning model exploits loopholes in a reward function to achieve high rewards without solving the intended task, poses a significant threat. This behavior may be explicit, i.e. verbalized in the model's…

Artificial Intelligence · Computer Science 2026-03-03 Xinpeng Wang , Nitish Joshi , Barbara Plank , Rico Angell , He He

Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…

Machine Learning · Computer Science 2021-10-07 Zifan Wang , Matt Fredrikson , Anupam Datta

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Machine Learning · Computer Science 2022-07-18 Xuhong Li , Haoyi Xiong , Xingjian Li , Xuanyu Wu , Xiao Zhang , Ji Liu , Jiang Bian , Dejing Dou

Deep learning models are widely used for various industrial and scientific applications. Even though these models have achieved considerable success in recent years, there exists a lack of understanding of the rationale behind decisions…

Machine Learning · Computer Science 2020-07-08 Swapnil Nitin Shah

This essay identifies a failure mode of AI chat systems that we term attribution laundering: the model performs substantive cognitive work and then rhetorically credits the user for having generated the resulting insights. Unlike…

Artificial Intelligence · Computer Science 2026-04-15 Aaron Tuor , claude. ai

Numerous explanation methods have been recently developed to interpret the decisions made by deep neural network (DNN) models. For image classifiers, these methods typically provide an attribution score to each pixel in the image to…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Ruo Yang , Binghui Wang , Mustafa Bilgic

Imputation is an attractive tool for dealing with the widespread issue of missing values. Consequently, studying and developing imputation methods has been an active field of research over the last decade. Faced with an imputation task and…

Methodology · Statistics 2025-07-16 Jeffrey Näf , Krystyna Grzesiak , Erwan Scornet

Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples. We present MIRAGE, a…

Computation and Language · Computer Science 2025-03-03 Jiachun Li , Pengfei Cao , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Thomas Fel

The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…

Machine Learning · Statistics 2023-04-04 Sung Min Park , Kristian Georgiev , Andrew Ilyas , Guillaume Leclerc , Aleksander Madry

As large language models take on growing roles as automated evaluators in practical settings, a critical question arises: Can individuals persuade an LLM judge to assign unfairly high scores? This study is the first to reveal that…

Computation and Language · Computer Science 2025-08-12 Yerin Hwang , Dongryeol Lee , Taegwan Kang , Yongil Kim , Kyomin Jung

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably…

Computation and Language · Computer Science 2026-02-10 Haoran Zhang , Yafu Li , Zhi Wang , Zhilin Wang , Shunkai Zhang , Xiaoye Qu , Yu Cheng

Feature attribution is often loosely presented as the process of selecting a subset of relevant features as a rationale of a prediction. Task-dependent by nature, precise definitions of "relevance" encountered in the literature are however…

Machine Learning · Computer Science 2021-07-12 Darius Afchar , Romain Hennequin , Vincent Guigue