# What is the Best Sequence Length for BABYLM?

arXiv: https://arxiv.org/abs/2510.19493 · HTML: https://mlsanity.com/paper/2510.19493/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://mlsanity.com/paper/2212.06713/) (2022)
- [Cramming: Training a Language Model on a Single GPU in One Day](https://mlsanity.com/paper/2212.14034/) (2022)
- [How to Train BERT with an Academic Budget](https://mlsanity.com/paper/2104.07705/) (2021)
- [A Simple and Effective Positional Encoding for Transformers](https://mlsanity.com/paper/2104.08698/) (2021)
- [BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop](https://mlsanity.com/paper/2502.10645/) (2025)
- [CLIMB: Curriculum Learning for Infant-inspired Model Building](https://mlsanity.com/paper/2311.08886/) (2023)
- [Linear Recency Bias During Training Improves Transformers' Fit to Reading Times](https://mlsanity.com/paper/2409.11250/) (2024)
- [Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition](https://mlsanity.com/paper/2502.04795/) (2025)
- [Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models](https://mlsanity.com/paper/2508.05803/) (2025)

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

- [Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction](https://mlsanity.com/paper/2510.20411/) (2025)
- [ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting](https://mlsanity.com/paper/2604.18452/) (2026)

## Abstract (arXiv)

Transformer language models typically operate with a fixed-length context window, which has grown in step with large-scale pretraining datasets. In the BabyLM Challenge, however, many past submissions have defaulted to using much shorter sequence lengths. We examine the impact of sequence length on BabyLM pretraining, to answer the simple question: what sequence length should we be using when training Baby LMs? Using 100M-word training data and fixed compute budgets, we compare 125M-parameter Mamba and OPT models, finding that although longer is often better, the optimal length depends on both task and architecture. Shorter sequences are sufficient for grammatical generalization tasks whereas longer contexts benefit morphological analogical reasoning tasks.