Metraipolis › archive › dc_79ff2753ef8f
SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI — arXiv:2610.41856
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41856
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T07:43:27.787Z
- SHA-256 of the archived text
64b33b39a1ed6cd735022cc7bf9bd9ad81bca5c2daed42d640f3e4a61d314e85- Stable URL of this page
https://metraipolis.com/documento/dc_79ff2753ef8f
How to cite
SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI — arXiv:2610.41856 — arXiv (en), https://arxiv.org/abs/2610.41856 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79ff2753ef8f (Metraipolis archive dc_79ff2753ef8f, sha256 64b33b39a1ed6cd735022cc7bf9bd9ad81bca5c2daed42d640f3e4a61d314e85)
BibTeX
@misc{dc79ff2753ef8f,
title = {SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI — arXiv:2610.41856},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41856},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79ff2753ef8f; sha256 64b33b39a1ed6cd735022cc7bf9bd9ad81bca5c2daed42d640f3e4a61d314e85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41856. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up questions. We present SimXAI, a lightweight LLM-centric conversational layer that replaces these modules with a single tool-calling LLM that bridges access to existing XAI resources. Rather than a standalone agent, SimXAI serves as a modular interface that enables conversational access to external XAI resources. We further introduce an evaluation suite for single- and multi-turn parsing, faithfulness, and contextualization. Across existing and new datasets, SimXAI achieves strong function-selection accuracy and high faithfulness while better handling context-dependent requests. In a user study replacing only the conversational layer of TalkToModel, a representative GUS-based agent, users completed tasks more accurately and in fewer turn. Overall, SimXAI improves GUS-based design while preserving faithfulness and improving conversational quality. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2610.41856 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T07:39:37.398Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).