Why Did the Robot Cross the Road? A User Study of Explanation in Human-Robot Interaction

我的机器人为什么刚改变了人格？面向基于大语言模型（LLM）的人机交互（HRI）的具身机器人人格提示设计指南

Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRI

本文针对基于LLM的HRI中机器人人格模糊等问题，提出含八个组件的提示设计框架及指南，为HRI研究提供结构化设计与报告辅助，强调提示设计需作为社会技术问题处理。

Explaining the Road Not Taken

It is unclear if existing interpretations of deep neural network models respond effectively to the needs of users. This paper summarizes the common forms of explanations (such as feature attribution, decision rules, or probes) used in over 200 recent papers about natural language processing (NLP), and compares them against user questions collected in the XAI Question Bank. We found that although users are interested in explanations for the road not taken -- namely, why the model chose one result and not a well-defined, seemly similar legitimate counterpart -- most model interpretations cannot …

Why Didn't You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models

To address the lack of comparative evaluation of Human-in-the-Loop Topic Modeling (HLTM) systems, we implement and evaluate three contrasting HLTM modeling approaches using simulation experiments. These approaches extend previously proposed frameworks, including constraints and informed prior-based methods. Users should have a sense of control in HLTM systems, so we propose a control metric to measure whether refinement operations' results match users' expectations. Informed prior-based methods provide better control than constraints, but constraints yield higher quality topics.

"If it didn't happen, why would I change my decision?": How Judges Respond to Counterfactual Explanations for the Public Safety Assessment

Many researchers and policymakers have expressed excitement about algorithmic explanations enabling more fair and responsible decision-making. However, recent experimental studies have found that explanations do not always improve human use of algorithmic advice. In this study, we shed light on how people interpret and respond to counterfactual explanations (CFEs) -- explanations that show how a model's output would change with marginal changes to its input(s) -- in the context of pretrial risk assessment instruments (PRAIs). We ran think-aloud trials with eight sitting U.S. state court judges…

感知差距：为什么我们需要为辅助技术提供可访问的XAI

The Perceptual Gap: Why We Need Accessible XAI for Assistive Technologies

本文探讨了为辅助技术用户提供可访问的XAI的重要性，指出现有XAI方法缺乏对感官障碍用户的考虑，并提出了未来研究的方向。

人们几乎做了什么：超越行为契合度的LLM社会模拟评估

What People Almost Did: Evaluating LLM Social Simulations Beyond Behavioral Fit

本文针对LLM社会模拟仅评估行为契合度的不足，提出“表征充分性”新目标，通过推理轨迹评估情景-推理-行动三元组对行为背后推理过程的忠实保留，以支持解释、诊断和干预比较等应用。