Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

About

Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language models (LLMs). However, the annotation efforts required to produce high quality responses for instructions are becoming prohibitively expensive, especially as the number of tasks spanned by instruction datasets continues to increase. Active learning is effective in identifying useful subsets of samples to annotate from an unlabeled pool, but its high computational cost remains a barrier to its widespread applicability in the context of LLMs. To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design. Experimental design techniques select the most informative samples to label, and typically maximize some notion of uncertainty and/or diversity. In our work, we implement a framework that evaluates several existing and novel experimental design techniques and find that these methods consistently yield significant gains in label efficiency with little computational overhead. On generative tasks, our methods achieve the same generalization performance with only $50\%$ of annotation cost required by random sampling.

Gantavya Bhatt, Yifang Chen, Arnav M. Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak• 2024

Related benchmarks

TaskDatasetResultRank
Medical ReasoningMedMCQA
Accuracy57.5
72
Medical ReasoningMedQA
Accuracy67.3
61
Medical ReasoningPubMedQA
Accuracy76.6
48
Medical Question AnsweringMedQA (test)
Accuracy68.8
28
Medical ReasoningMedical Reasoning Evaluation Suite m23k
Average Performance54.3
25
Medical Question AnsweringMedBullets (test)
Accuracy0.547
24
Medical Question AnsweringMedXpert (test)
Accuracy16.1
21
Medical ReasoningMMLU-Pro
Accuracy62.5
18
Medical ReasoningMedXpert
Accuracy15.8
14
Medical Question AnsweringMedMCQA (val)
Accuracy58.7
10
Showing 10 of 24 rows

Other info

Follow for update