Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916673989115904 |
|---|---|
| author | Krupp, Lars Geißler, Daniel Hevesi, Peter Hirsch, Marco Lukowicz, Paul Karolus, Jakob |
| author_facet | Krupp, Lars Geißler, Daniel Hevesi, Peter Hirsch, Marco Lukowicz, Paul Karolus, Jakob |
| contents | Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03343 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web Krupp, Lars Geißler, Daniel Hevesi, Peter Hirsch, Marco Lukowicz, Paul Karolus, Jakob Artificial Intelligence Human-Computer Interaction Information Retrieval Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web. |
| title | Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web |
| topic | Artificial Intelligence Human-Computer Interaction Information Retrieval |
| url | https://arxiv.org/abs/2504.03343 |