# SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI

**Authors:** Van Bach Nguyen, Qianli Wang, Nils Feldhus, Jörg Schlötterer, Christin Seifert  
**Lab:** Philipps University of Marburg · **Published:** 30 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.41856) · [PDF](https://arxiv.org/pdf/2610.41856) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.41856.html)

## Abstract

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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.