Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BLADE: Better Language Answers through Dialogue and Explanations

Chathuri Jayaweera, Bonnie J. Dorr

Abstract

Large language model (LLM)-based educational assistants often provide direct answers that short-circuit learning by reducing exploration, self-explanation, and engagement with course materials. We present BLADE (Better Language Answers through Dialogue and Explanations), a grounded conversational assistant that guides learners to relevant instructional resources rather than supplying immediate solutions. BLADE uses a retrieval-augmented generation (RAG) framework over curated course content, dynamically surfacing pedagogically relevant excerpts in response to student queries. Instead of delivering final answers, BLADE prompts direct engagement with source materials to support conceptual understanding. We conduct an impact study in an undergraduate computer science course, with different course resource configurations and show that BLADE improves students' navigation of course resources and conceptual performance compared to simply providing the full inventory of course resources. These results demonstrate the potential of grounded conversational AI to reinforce active learning and evidence-based reasoning.

BLADE: Better Language Answers through Dialogue and Explanations

Abstract

Large language model (LLM)-based educational assistants often provide direct answers that short-circuit learning by reducing exploration, self-explanation, and engagement with course materials. We present BLADE (Better Language Answers through Dialogue and Explanations), a grounded conversational assistant that guides learners to relevant instructional resources rather than supplying immediate solutions. BLADE uses a retrieval-augmented generation (RAG) framework over curated course content, dynamically surfacing pedagogically relevant excerpts in response to student queries. Instead of delivering final answers, BLADE prompts direct engagement with source materials to support conceptual understanding. We conduct an impact study in an undergraduate computer science course, with different course resource configurations and show that BLADE improves students' navigation of course resources and conceptual performance compared to simply providing the full inventory of course resources. These results demonstrate the potential of grounded conversational AI to reinforce active learning and evidence-based reasoning.

Paper Structure

This paper contains 15 sections, 7 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. BLADE System Architecture
  4. Curriculum-Aware Content Indexing
  5. Instructional Relevance Retrieval
  6. Evidence-Focused Dialogue Generation
  7. Classroom Deployment and Evaluation
  8. Resource Configurations
  9. Group Assignments
  10. Results
  11. Correct Answer Selection and Overall Performance
  12. The usage of provided resources
  13. Conclusions
  14. Future Work
  15. Limitations

Figures (7)

  • Figure 1: The BLADE interaction paradigm, in which a curriculum-aware conversational assistant retrieves and highlights relevant instructional resources in response to student queries. Instead of supplying final answers, BLADE directs learners to evidence within course materials, supporting explanation-centered learning and active resource exploration.
  • Figure 2: An example of a typical BLADE response to a query with citations of sources. The cited sources include textbook/course material excerpts as well as lecture transcripts with timestamps of the relevant portion.
  • Figure 3: Distribution of upper-performance who picked the correct answer in each quiz, normalized by the total number of quiz-takers.
  • Figure 4: Distribution of lower-performance students who picked the correct answer in each quiz, normalized by the total number of quiz-takers.
  • Figure 6: Distribution of mid-performance students who picked the correct answer in each quiz, normalized by the total number of quiz-takers.
  • ...and 2 more figures