OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization

Abstract

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

arXiv comment56 pages. v2->v3: fix OPT-30B evaluation results across benchmarks (previously we reported lower performance of this model due to an evaluation pipeline bug)

Cited by in corpus (8)

• Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization
• A Survey on Symbolic Knowledge Distillation of Large Language Models
• An Evaluation on Large Language Model Outputs: Discourse and Memorization
• ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models
• Learning to Paraphrase Sentences to Different Complexity Levels
• Complex QA and language models hybrid architectures, Survey
• OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
• Simple and Effective Input Reformulations for Translation