Explaining the decision-making process of machine learning models is crucial for ensuring their reliability and transparency for end users. One popular explanation form highlights key input features, such as i) tokens (e.g., Shapley Values and Integrated Gradients), ii) interactions between tokens (e.g., Bivariate Shapley and Attention-based methods), or iii) interactions between spans of the input (e.g., Louvain Span Interactions). However, these explanation types have only been studied in isolation, making it difficult to judge their respective applicability. To bridge this gap, we develop a unified framework that facilitates an automated and direct comparison between highlight and interactive explanations comprised of four diagnostic properties. We conduct an extensive analysis across these three types of input feature explanations -- each utilizing three different explanation techniques -- across two datasets and two models, and reveal that each explanation has distinct strengths across the different diagnostic properties. Nevertheless, interactive span explanations outperform other types of input feature explanations across most diagnostic properties. Despite being relatively understudied, our analysis underscores the need for further research to improve methods generating these explanation types. Additionally, integrating them with other explanation types that perform better in certain characteristics could further enhance their overall effectiveness.
Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations
Faculty of Computer Science, University of Vienna(计算机科学系,维也纳大学);UniVie Doctoral School Computer Science, University of Vienna(UniVie 计算机科学博士学院,维也纳大学);Faculty of Philological and Cultural Studies, University of Vienna(文学与文化研究系,维也纳大学)
Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset
ALTA Institute, Computer Laboratory, University of Cambridge(ALTA研究所、计算机实验室、剑桥大学);SB Intuitions;Tohoku University(东北大学);RIKEN(日本理化学研究所);The University of Sheffield(谢菲尔德大学)
The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems
Computational Linguistics, Department of Linguistics, Bielefeld University(语言学计算系,语言学系,比勒菲尔德大学);Honda Research Institute Europe(本田欧洲研究院);Digital Linguistics Lab, Department of Linguistics, Bielefeld University(数字语言学实验室,语言学系,比勒菲尔德大学)
Select or Project? Evaluating Lower-dimensional Vectors for LLM Training Data Explanations
Faculty of Computer Science, University of Vienna(维也纳大学计算机科学系);UniVie Doctoral School Computer Science, University of Vienna(维也纳大学计算机科学博士学院);Faculty of Philological and Cultural Studies, University of Vienna(维也纳大学文学与文化研究系)
MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation
University of Southern California(南加州大学);São Paulo State University(圣保罗州立大学);Saarland University(萨尔兰大学);University of Melbourne(墨尔本大学);Howard University(霍华德大学);Portland State University(波特兰州立大学);Leiden University(莱顿大学)
Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations
University of Tehran(德黑兰大学);Tehran University of Medical Sciences(德黑兰医科大学);Advanced Diagnostic and Interventional Radiology Research Center (ADIR)(高级诊断与介入放射学研究中心(ADIR))
From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment
Technical University of Munich(慕尼黑技术大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Lund University(吕勒奥大学);University of Tübingen(图宾根大学);Stanford Graduate School of Education(斯坦福大学教育研究生院);Harvard Graduate School of Education(哈佛大学教育研究生院)
SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy
University of Tübingen(蒂宾根大学);Technical University of Munich(慕尼黑工业大学);University Clinic Tübingen(蒂宾根大学医院);Hertie Institute for Clinical Brain Research(赫蒂临床脑研究所);Excellence Cluster Machine Learning, Tübingen University(蒂宾根大学机器学习卓越集群);Hertie Institute for AI in Brain Health (Hertie AI)(赫蒂人工智能脑健康研究所)
Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases
Center for Biomedical Data Science, Duke-NUS Medical School(生物医学数据科学中心,杜克 - 新加坡国立大学医学院);Duke-NUS AI + Medical Sciences Initiative, Duke-NUS Medical School(杜克 - 新加坡国立大学人工智能与医学科学计划,杜克 - 新加坡国立大学医学院);Department of Population Health Sciences, Weill Cornell Medicine(人口健康科学系,威尔康奈尔医学院);System Engineering, College of Engineering, Cornell University(系统工程,康奈尔大学工程学院);Graduate School of Frontier Sciences, The University of Tokyo(前沿科学研究生院,东京大学);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Department of Biostatistics and Bioinformatics, Duke University(生物统计学与生物信息学系,杜克大学);Perelman School of Medicine, University of Pennsylvania(佩雷尔曼医学院,宾夕法尼亚大学);School of Clinical Medicine, University of Cambridge(临床医学学院,剑桥大学);Hospital of the University of Pennsylvania(宾夕法尼亚大学医院);Children’s Hospital of Philadelphia (CHOP)(费城儿童医院);Department of Anatomic Pathology and Laboratory Medicine, Hospital of the University of Pennsylvania(解剖病理学与检验医学系,宾夕法尼亚大学医院);Department of Pathology and Laboratory Medicine, University of California, San Francisco(病理学与检验医学系,加州大学旧金山分校);Language Technologies Institute, Carnegie Mellon University(语言技术研究所,卡内基梅隆大学)
SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence
Beijing University of Technology(北京工业大学);Beijing Institute of Technology(北京理工大学);China-Japan Friendship Hospital(中日友好医院);Dongbei University of Finance and Economics(东北财经大学)