# llinstruct: An Instruction-tuned model for English Language Proficiency Assessments

arXiv: https://arxiv.org/abs/2410.09314 · HTML: https://mlsanity.com/paper/2410.09314/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 12 Oct 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Identifying Fairness Issues in Automatically Generated Testing Content](https://mlsanity.com/paper/2404.15104/) (2024)

## Abstract (arXiv)

We present llinstruct: An 8B instruction-tuned model that is designed to generate content for English Language Proficiency Assessments (ELPA) and related applications. Our work involves creating a new dataset of 70K instructions and explanations in the ELPA domain and using these to fine-tune Llama-3 8B models (SFT) of different sizes (e.g., SFT-17K, SFT-50K and SFT-70K). Human evaluations are conducted over unseen instructions to compare these SFT models against SOTA models (e.g., Dolly-2, Mistral, Llama-3 base version, and GPT-3.5). The findings show although all three SFT models perform comparably, the model trained on largest instruction dataset -- SFT-70K - leads to the most valid outputs ready for assessments. However, although the SFT models perform better than larger model, e.g., GPT 3.5 on the aspect of explanations of outputs, many outputs still need human interventions to make them actual ready for real world assessments.