paper-with-me

Papers

Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition

2020-05-05 · Mahsan Nourani, Chiradeep Roy, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate

Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system.

📄 PDF Abstract BibTeX arXiv:2005.02335

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionDecision Making

Similar Papers 제목 키워드 기반

Explainable Automated Fact-Checking for Public Health Claims

2020-10-19 · EMNLP 2020 11 · Neema Kotonya, Francesca Toni

Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast majority of fact-checking studies focus exclusively on political claims. Very little researc…

Explanation GenerationFact Checking

A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM

2026-04-08 · Bo Wang, Jing Ma, Hongzhan Lin, Zhiwei Yang 외 arxiv

Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with brea…

Explanation GenerationFake News Detection

Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification

2023-05-16 · Jiasheng Si, Yingjie Zhu, Deyu Zhou

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One possible way is erasure search: obtaining the rationale by entirely removi…

DiagnosticFact VerificationSentence

Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models

2024-05-15 · Majid Zarharan, Pascal Wullschleger, Babak Behkam Kia, Mohammad Taher Pilehvar 외

This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or justi…

Explanation GenerationFact Checkingparameter-efficient fine-tuning

AMREx: AMR for Explainable Fact Verification

2024-11-02 · Chathuri Jayaweera, Sangpil Youm, Bonnie Dorr

With the advent of social media networks and the vast amount of information circulating through them, automatic fact verification is an essential component to prevent the spread of misinformation. It is even more useful …

Abstract Meaning RepresentationClaim VerificationFact VerificationMisinformation