SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI
cs.CL, cs.AI, cs.HC
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted at EMNLP 2026 Findings
Code: https://github.com/bach-mr/SimXAI
License: http://creativecommons.org/licenses/by/4.0/
The gist: Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation.
Terminology
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.
Sources
- The Llama 3 Herd of Models
- Rethinking Explainability as a Dialogue: A Practitioner's Perspective
- Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
- KnowThyself: An Agentic Assistant for LLM Interpretability
- Gemma 3 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data