ACL Findings2021
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations
Ana Valeria Gonzalez, Gagan Bansal, Angela Fan, Yashar Mehdad, Robin Jia, Srinivasan Iyer
Abstract
While research on explaining predictions of open-domain QA systems (ODQA) is gaining momentum, most works do not evaluate whether these explanations improve user trust.Furthermore, many users interact with ODQA using voice-assistants, yet prior works exclusively focus on visual displays, risking (as we also show) incorrectly extrapolating the effectiveness of explanations across modalities.To better understand the effectiveness of ODQA explanations strategies in the wild, we conduct user studies that measure whether explanations help users correctly decide when to accept or reject an ODQA system's answer.Unlike prior work, we control for explanation modality, i.e., whether they are communicated to users through a spoken or visual interface, and contrast effectiveness across modalities.We show that explanations derived from retrieved evidence can outperform strong baselines across modalities but the best explanation strategy varies with the modality.We show common failure cases of current explanations, emphasize end-to-end evaluation of explanations, and caution against evaluating them in proxy modalities that differ from deployment.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
7 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance cites Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?
- Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? cites ERASER: A Benchmark to Evaluate Rationalized NLP Models
- Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations cites Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
- Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations cites Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales
- Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies cites Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
- AmbigQA: Answering Ambiguous Open-domain Questions cites Dense Passage Retrieval for Open-Domain Question Answering
- Seamful XAI: Operationalizing Seamful Design in Explainable AI cites Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
- Presenting Large Language Models as Companions Affects What Mental Capacities People Attribute to Them cites Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
- Presenting Large Language Models as Companions Affects What Mental Capacities People Attribute to Them cites Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies
Cited by top-tier papers7
- Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and InconsistenciesSunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, Tania Lombrozo et al.CHI 2025 · 118 citations
- Seamful XAI: Operationalizing Seamful Design in Explainable AIUpol Ehsan, Q. Vera Liao, Samir Passi, Mark O. Riedl et al.CSCW 2024 · 41 citations
- Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text RationalesBrihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan et al.ACL 2023 · 6 citations
- Presenting Large Language Models as Companions Affects What Mental Capacities People Attribute to ThemAllison Chen, Sunnie S. Y. Kim, Angel Nathaniel Franyutti-Cintron, Amaya Dharmasiri et al.CHI 2026 · 3 citations
- Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model ExplanationsKeyu He, Tejas Srinivasan, Brihi Joshi, Xiang Ren et al.ACL 2026
Builds on7
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team PerformanceGagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok et al.CHI 2021 · 713 citations
- Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?Peter Hase, Mohit BansalACL 2020 · 216 citations
- AmbigQA: Answering Ambiguous Open-domain QuestionsSewon Min, Julian Michael, Hannaneh Hajishirzi, Luke ZettlemoyerEMNLP 2020 · 162 citations
- Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
- ERASER: A Benchmark to Evaluate Rationalized NLP ModelsJay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric P. Lehman et al.ACL 2020 · 36 citations
Related papers
- Does Explainable Artificial Intelligence Improve Human Decision-Making?Yasmeen Alufaisan, Laura R. Marusich, Jonathan Z. Bakdash, Yan Zhou et al.AAAI 2021 · 135 citations
- Explainability for Transparent Conversational Information-SeekingWeronika Lajewska, Damiano Spina, Johanne R. Trippas, Krisztian BalogSIGIR 2024 · 17 citations
- Understanding the impact of explanations on advice-taking: a user study for AI-based clinical Decision Support SystemsCecilia Panigutti, Andrea Beretta, Fosca Giannotti, Dino PedreschiCHI 2022 · 129 citations
- Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-DeploymentZichao Li, Prakhar Sharma, Xing Han Lù, Jackie Chi Kit Cheung et al.ACL Findings 2022 · 14 citations
- Explaining Model Confidence Using CounterfactualsThao Le, Tim Miller, Ronal Singh, Liz SonenbergAAAI 2023 · 9 citations
