多模态 LLM 生成的解释能否提升用户对 XAI 可视化的理解与信任?arXiv 实验研究
Can AI Help Explain AI? Effects of Multimodal LLM-Generated Explanations on Perceived Understanding and Perceived Trust in XAI Visualizations
AI 导读
一项预注册被试内实验(N=128)评估多模态 LLM 文本解释能否改善 XAI 可视化的可读性。结果显示,添加 LLM 解释使感知理解和感知信任在五点量表上分别提升 0.35 和 0.26 分(均 p<.001),增益覆盖全部七个决策场景和五种 XAI 方法,且对先前 XAI 经验最少的被试效果最大。中介分析表明 LLM 解释通过感知理解间接提升感知信任。
正文 · 原文
Abstract:Explainable artificial intelligence (XAI) aims to make machine learning models understandable, yet many XAI visualizations remain difficult for end-users to interpret. Here, we evaluate whether augmenting XAI outputs with textual explanations from multimodal LLMs improves perceived understanding and perceived trust. We conducted a pre-registered within-subject experiment ($N = 128$) across seven decision scenarios and five XAI methods, with and without LLM generated explanations. The explanations improved perceived understanding and perceived trust by 0.35 and 0.26 points on five-point scales (both $p < .001$). The gain appeared in all seven scenarios, did not differ between local and global explanations, and was largest for participants with the least prior XAI exposure. A mediation analysis indicates an indirect effect on perceived trust through perceived understanding. These results suggest that multimodal LLMs can provide a useful interpretive layer for XAI beyond expert audiences.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21638 [cs.HC] |
| (or arXiv:2611.21638v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21638 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mario Truss [view email]
[v1]
Fri, 25 Sep 2026 08:11:14 UTC (7,029 KB)
来源:arXiv cs.AI · arxiv.org