English(EN) Correct Yourself, Keep My Trust: How Self-Correction and Social Connection Shape Credibility in Social Chatbots

研究发现，能够自我纠错的聊天机器人能更好地维持用户信任

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-17 17:04

一项发表在arXiv上的新研究探讨了社交聊天机器人在犯错后如何维持用户信任。研究人员发现，与依赖外部来源纠错的聊天机器人相比，能够自我纠错的聊天机器人被认为更值得信赖、更具专业性。研究还强调，与聊天机器人建立牢固的社交联系会增强自我纠错的有效性，对信念的改变产生更显著的影响。 AI

影响这项研究表明，对于设计用于社交互动的人工智能系统而言，自我纠错对于维持用户信任和参与度至关重要。

排序理由该集群包含一篇详细介绍聊天机器人行为实验结果的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Biswadeep Sen, Yi-Chieh Lee · 2026-06-18 04:00

Correct Yourself, Keep My Trust: How Self-Correction and Social Connection Shape Credibility in Social Chatbots

arXiv:2606.19286v1 Announce Type: cross Abstract: When social chatbots make mistakes, and they do, how they recover determines whether users trust them again. Social chatbots are increasingly integrated into everyday life, yet they remain prone to generating convincing but inaccu…
arXiv cs.AI TIER_1 English(EN) · Yi-Chieh Lee · 2026-06-17 17:04

纠正自己，赢得信任：自我纠正与社交联系如何塑造社交聊天机器人的可信度

When social chatbots make mistakes, and they do, how they recover determines whether users trust them again. Social chatbots are increasingly integrated into everyday life, yet they remain prone to generating convincing but inaccurate information. The social connection they build…