Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

Simran Kaur, Simon Park, Anirudh Goyal, Sanjeev Arora

Keywords: instruction tuning, high quality synthetic data, diverse synthetic data

TL;DR: We introduce an automated approach for creating diverse, high quality SFT data for instruction-following.

Abstract:

We introduce INSTRUCT-SKILLMIX, an automated approach for creating diverse, high quality SFT data for instruction-following. The pipeline involves two stages, each leveraging an existing powerful LLM: (1) Skill extraction: uses the LLM to extract core “skills” for instruction-following by directly prompting the model. This is inspired by “LLM metacognition” of (Didolkar et al., 2024); (2) Data generation: uses the powerful LLM to generate (instruction, response) data that
exhibit a randomly chosen pair of these skills. Here, the use of random skill combinations promotes diversity and difficulty. The estimated cost of creating the dataset is under $600.

Vanilla SFT (i.e., no PPO, DPO, or RL methods) on data generated from INSTRUCT-SKILLMIX leads to strong gains on instruction following benchmarks such as AlpacaEval 2.0, MT-Bench, and WildBench. With just 4K examples, LLaMA-3-8B-Base achieves 42.76% length-controlled win rate on AlpacaEval 2.0, a level similar to frontier models like Claude 3 Opus and LLaMA-3.1-405B-Instruct. Ablation studies also suggest plausible reasons for why creating open instruction-tuning datasets via naive crowd-sourcing has proved difficult. In our dataset,adding 20% low quality answers (“shirkers”) causes a noticeable degradation in performance.

The INSTRUCT-SKILLMIX pipeline seems flexible and adaptable to other settings.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11917