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

A lightweight LLM-centric conversational layer called SimXAI replaces the separate intent-recognition, dialogue-management and template-generation modules of GUS-style conversational explainable AI agents with a single tool-calling LLM, according to arXiv paper 2610.41856v1. In a user study that swapped only the conversational layer of TalkToModel, a representative GUS-based agent, users completed tasks more accurately and in fewer turns, while SimXAI also achieved strong function-selection accuracy and high faithfulness across existing and new datasets. The authors also introduce an evaluation suite for single- and multi-turn parsing, faithfulness and contextualization, positioning SimXAI as a modular interface to external XAI resources rather than a standalone agent.

arXiv:2610.41856v1 Announce Type: new 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.