PulseAugur
EN
LIVE 02:38:24

LLM dialogue system explains recommendations to improve teacher trust

By PulseAugur Editorial · [2 sources] ·

Researchers have developed an explainable dialogue system using a fine-tuned large language model (LLM) to aid teachers in diagnosing student problem behaviors. The system employs a hierarchical attribution method from explainable AI (xAI) to identify evidence within dialogues and generate natural-language explanations for its recommendations. A preliminary study with 22 pre-service teachers indicated that those who received explanations reported increased trust in the system. AI

IMPACT Enhances trust in LLM-based educational tools by providing transparent reasoning for diagnostic recommendations.

RANK_REASON Academic paper detailing a new explainable AI method for LLM-based dialogue systems.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

LLM dialogue system explains recommendations to improve teacher trust

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Zhilin Fan, Deliang Wang, Penghe Chen, Yu Lu ·

    Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

    arXiv:2604.22237v1 Announce Type: new Abstract: Diagnosing student problem behaviors requires teachers to synthesize multifaceted information, identify behavioral categories, and plan intervention strategies. Although fine-tuned large language models (LLMs) can support this proce…

  2. arXiv cs.CL TIER_1 English(EN) · Yu Lu ·

    Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

    Diagnosing student problem behaviors requires teachers to synthesize multifaceted information, identify behavioral categories, and plan intervention strategies. Although fine-tuned large language models (LLMs) can support this process through multi-turn dialogue, they rarely expl…

RELATED ENTITIES

RELATED TOPICS