← 研踪 PaperTrailarXiv:2511.19123 · v3
Facilitating the Integration of LLMs Into Online Experiments With Simple Chat
首次提交 2025-11-24 21:52
版本更新 2026-11-09 01:41
雷达观测 2026-11-10 13:19
摘要
As large language models (LLMs) become increasingly prevalent, understanding human-LLM interactions is emerging as a central priority in psychological research. Online experiments offer an efficient means to study human-LLM interactions, yet integrating LLMs into established survey platforms remains technically demanding, particularly when aiming for ecologically realistic, real-time conversational experiences with strong experimental control. We introduce Simple Chat, an open-source, research-focused chat interface that streamlines LLM integration for platforms such as Qualtrics, oTree, and LimeSurvey, while presenting a unified participant experience across conditions. Simple Chat connects to both commercial providers and open-weights models, displays streamed responses incrementally, and offers an administrative interface for fine-grained control of prompts and interface features. Simple Chat is available both as a hosted service that requires no installation and as open-source software that researchers can deploy on their own server or adapt to their needs. By reducing technical barriers and standardizing interfaces, Simple Chat helps advance the study of human-LLM interaction. In this article, we outline Simple Chat's key features, provide a step-by-step tutorial, and demonstrate its utility through two illustrative case studies.
作者备注：Revised version
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-09 01:41 · 最新观测版本
Facilitating the Integration of LLMs Into Online Experiments With Simple Chat
As large language models (LLMs) become increasingly prevalent, understanding human-LLM interactions is emerging as a central priority in psychological research. Online experiments offer an efficient means to study human-LLM interactions, yet integrating LLMs into established survey platforms remains technically demanding, particularly when aiming for ecologically realistic, real-time conversational experiences with strong experimental control. We introduce Simple Chat, an open-source, research-focused chat interface that streamlines LLM integration for platforms such as Qualtrics, oTree, and LimeSurvey, while presenting a unified participant experience across conditions. Simple Chat connects to both commercial providers and open-weights models, displays streamed responses incrementally, and offers an administrative interface for fine-grained control of prompts and interface features. Simple Chat is available both as a hosted service that requires no installation and as open-source software that researchers can deploy on their own server or adapt to their needs. By reducing technical barriers and standardizing interfaces, Simple Chat helps advance the study of human-LLM interaction. In this article, we outline Simple Chat's key features, provide a step-by-step tutorial, and demonstrate its utility through two illustrative case studies.
查看此版本解读 →查看此版本原文 ↗