Apr 27
Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis
★★★★★
significance 2/5
Researchers developed an explainable dialogue system using a fine-tuned LLM to help teachers diagnose student behaviors. The system uses a hierarchical attribution method to provide natural-language explanations for its recommendations, which increased user trust during preliminary testing.
Why it matters
Bridging the gap between diagnostic accuracy and user trust through natural-language explanations is critical for deploying LLMs in sensitive educational environments.
Tags
#explainable ai #llm #education #xai #dialogue systemsRelated coverage
- Global South OpportunitiesPivotal Research Fellowship 2026 (Q3): AI Safety Research Opportunity - Global South Opportunities
- arXiv cs.AIAn Intelligent Fault Diagnosis Method for General Aviation Aircraft Based on Multi-Fidelity Digital Twin and FMEA Knowledge Enhancement
- arXiv cs.AIPExA: Parallel Exploration Agent for Complex Text-to-SQL
- arXiv cs.AIThe Power of Power Law: Asymmetry Enables Compositional Reasoning
- arXiv cs.AIOn the Existence of an Inverse Solution for Preference-Based Reductions in Argumentation