# Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation

arXiv: https://arxiv.org/abs/2506.07626 · HTML: https://mlsanity.com/paper/2506.07626/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 14 of 14)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems](https://mlsanity.com/paper/2305.14536/) (2023)
- [A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets](https://mlsanity.com/paper/2305.18486/) (2023)
- [Controlled Text Generation with Natural Language Instructions](https://mlsanity.com/paper/2304.14293/) (2023)
- [Large Language Models in Education: Vision and Opportunities](https://mlsanity.com/paper/2311.13160/) (2023)
- [Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes](https://mlsanity.com/paper/2310.10648/) (2023)
- [AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails](https://mlsanity.com/paper/2402.09216/) (2024)
- [FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs](https://mlsanity.com/paper/2409.13540/) (2024)
- [Instructors as Innovators: A future-focused approach to new AI learning opportunities, with prompts](https://mlsanity.com/paper/2407.05181/) (2024)
- [Fine-Tuning Large Language Models for Educational Support: Leveraging Gagne's Nine Events of Instruction for Lesson Planning](https://mlsanity.com/paper/2503.09276/) (2025)

## Built on by (most cited first, 8 of 8)

- [Opportunities and Challenges of LLMs in Education: An NLP Perspective](https://mlsanity.com/paper/2507.22753/) (2025)
- [IntentGrasp: A Comprehensive Benchmark for Intent Understanding](https://mlsanity.com/paper/2605.06832/) (2026)
- [Codebook-Injected Dialogue Segmentation for Multi-Utterance Constructs Annotation: LLM-Assisted and Gold-Label-Free Evaluation](https://mlsanity.com/paper/2601.12061/) (2026)
- [Incentives Of EdTech: A Systematic Review Of EduNLP Research](https://mlsanity.com/paper/2606.13691/) (2026)
- [Examining Variation in How Guided AI Tutors Resolve Student Impasses](https://mlsanity.com/paper/2609.38346/) (2026)
- [DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring](https://mlsanity.com/paper/2610.04825/) (2026)
- [Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop](https://mlsanity.com/paper/2610.15692/) (2026)
- [A Unified Response Framework for Questions and Tutoring Dialogues](https://mlsanity.com/paper/2610.19532/) (2026)

## Abstract (arXiv)

Large language models (LLMs) hold great promise for educational applications, particularly in intelligent tutoring systems. However, effective tutoring requires alignment with pedagogical strategies - something current LLMs lack without task-specific adaptation. In this work, we explore whether fine-grained annotation of teacher intents can improve the quality of LLM-generated tutoring responses. We focus on MathDial, a dialog dataset for math instruction, and apply an automated annotation framework to re-annotate a portion of the dataset using a detailed taxonomy of eleven pedagogical intents. We then fine-tune an LLM using these new annotations and compare its performance to models trained on the original four-category taxonomy. Both automatic and qualitative evaluations show that the fine-grained model produces more pedagogically aligned and effective responses. Our findings highlight the value of intent specificity for controlled text generation in educational settings, and we release our annotated data and code to facilitate further research.