# Grammar Control in Dialogue Response Generation for Language Learning Chatbots

arXiv: https://arxiv.org/abs/2502.07544 · HTML: https://mlsanity.com/paper/2502.07544/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations](https://mlsanity.com/paper/2308.11995/) (2023)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation](https://mlsanity.com/paper/2308.16797/) (2023)
- [Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4](https://mlsanity.com/paper/2306.12794/) (2023)
- [User Adaptive Language Learning Chatbots with a Curriculum](https://mlsanity.com/paper/2304.05489/) (2023)
- [Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation](https://mlsanity.com/paper/2402.12593/) (2024)

## Built on by (most cited first, 2 of 2)

- [Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation](https://mlsanity.com/paper/2604.04450/) (2026)
- [Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners](https://mlsanity.com/paper/2604.22542/) (2026)

## Abstract (arXiv)

Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control grammar in chatbot conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We also explore how this control helps learners to produce specific grammar. We comprehensively evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Strategically decoding Llama3 outperforms GPT-3.5 when tolerating minor response quality losses. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. Existing language learning chatbots and research on second language acquisition benefit from these affordances. Code available on GitHub.