---
title: "SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.41856v1"
permalink: "https://feed.astralor.com/items/itm_36532e9aff02012e5fb330b5"
published: "2026-10-30T15:11:47.000Z"
score: 55
channel: "ai"
tags: ["LLM","AI Agent","推理效率","SimXAI","Simple Drop-in Layer","Increases Interaction Quality","Understanding","Conversational XAI Conversational"]
---

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

## At a glance

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 underlyin…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_36532e9aff02012e5fb330b5