# Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

arXiv: https://arxiv.org/abs/2510.20411 · HTML: https://mlsanity.com/paper/2510.20411/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 72 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 26 of 26)

- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [ORPO: Monolithic Preference Optimization without Reference Model](https://mlsanity.com/paper/2403.07691/) (2024)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [Emergent Communication through Negotiation](https://mlsanity.com/paper/1804.03980/) (2018)
- [Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty](https://mlsanity.com/paper/2308.02019/) (2023)
- [Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2412.05149/) (2024)
- [GPT or BERT: why not both?](https://mlsanity.com/paper/2410.24159/) (2024)
- [Is Child-Directed Speech Effective Training Data for Language Models?](https://mlsanity.com/paper/2408.03617/) (2024)
- [Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations](https://mlsanity.com/paper/2405.13828/) (2024)
- [Searching for Structure: Investigating Emergent Communication with Large Language Models](https://mlsanity.com/paper/2412.07646/) (2024)
- [Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models](https://mlsanity.com/paper/2505.23689/) (2025)
- [NeLLCom-X: A Comprehensive Neural-Agent Framework to Simulate Language Learning and Group Communication](https://mlsanity.com/paper/2407.13999/) (2024)
- [KidLM: Advancing Language Models for Children -- Early Insights and Future Directions](https://mlsanity.com/paper/2410.03884/) (2024)
- [Rubrik's Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset](https://mlsanity.com/paper/2503.23899/) (2025)
- [Supervised Seeded Iterated Learning for Interactive Language Learning](https://mlsanity.com/paper/2010.02975/) (2020)
- [The Curious Case of Representational Alignment: Unravelling Visio-Linguistic Tasks in Emergent Communication](https://mlsanity.com/paper/2407.17960/) (2024)
- [Investigating the Zone of Proximal Development of Language Models for In-Context Learning](https://mlsanity.com/paper/2502.06990/) (2025)
- [Simulating the Emergence of Differential Case Marking with Communicating Neural-Network Agents](https://mlsanity.com/paper/2502.04038/) (2025)
- [Towards Interactive Language Modeling](https://mlsanity.com/paper/2112.11911/) (2021)
- [Yes, this Way! Learning to Ground Referring Expressions into Actions with Intra-episodic Feedback from Supportive Teachers](https://mlsanity.com/paper/2305.12880/) (2023)
- [What is the Best Sequence Length for BABYLM?](https://mlsanity.com/paper/2510.19493/) (2025)

## Built on by (most cited first, 9 of 9)

- [BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop](https://mlsanity.com/paper/2602.20092/) (2026)
- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)

## Abstract (arXiv)

Multi-turn dialogues between a child and a caregiver are characterized by a property called contingency - that is, prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a teacher-student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words. Using a novel alignment dataset for post-training, BabyLM generates responses that are more grammatical and cohesive. Experiments with adaptive teacher decoding strategies show limited additional gains. ContingentChat demonstrates the benefits of targeted post-training for dialogue quality and indicates that contingency remains a challenging goal for BabyLMs.