# Non-instructional Fine-tuning: Enabling Instruction-Following Capabilities in Pre-trained Language Models without Instruction-Following Data

arXiv: https://arxiv.org/abs/2409.00096 · HTML: https://mlsanity.com/paper/2409.00096/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 11 of 11)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing](https://mlsanity.com/paper/2406.08464/) (2024)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [An Empirical Study of Instruction-tuning Large Language Models in Chinese](https://mlsanity.com/paper/2310.07328/) (2023)

## Built on by (most cited first, 1 of 1)

- [News Reporter: A Multi-lingual LLM Framework for Broadcast T.V News](https://mlsanity.com/paper/2410.07520/) (2024)

## Abstract (arXiv)

Instruction fine-tuning is crucial for today's large language models (LLMs) to learn to follow instructions and align with human preferences. Conventionally, supervised data, including the instruction and the correct response, is required for instruction fine-tuning. To obtain such data, some researchers prompted well-trained models like GPT-4 to generate instructions and correct responses. In this paper, we propose a novel approach that uses the first half of a random text from OpenWebText as the instruction and GPT-3.5-turbo or GPT-4-turbo to complete the text as the response. Despite the data being "non-instructional", we found that pre-trained LLMs fine-tuned on this data can gain instruction-following capabilities. This observation is verified by fine-tuning several well-known pre-trained LLMs (e.g., LLaMA-2-7B, LLaMA-3-8B, LLaMA-3-70B, Mistral-7B-v0.1). The "non-instructional data" also improved some models that underwent supervised fine-tuning and human preference alignment. Our LLaMA-3-70B-Instruct fine-tuned through "non-instructional data" is comparable with LLaMA-3.1-70B-Instruct on the Arena Hard leaderboard. We analyzed the "non-instructional data" and ensured it is devoid of content related to instruction fine-tuning. Our findings will inspire further investigation into how to develop instruction-following capabilities without explicit instruction-related data.