FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Preprint
Abstract
Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning. Each of these comes with their own trade-offs based on available data, model size, compute cost, ease-of-use, and final quality with neither solution performing well across-the-board. In this article, we first describe ICL and fine-tuning paradigms in a way that highlights their natural connections. Based on these connections, we propose a new learning paradigm called FIAT that fuses the best of these paradigms together, enabling prompt-engineered instructions and chain-of-thought reasoning with the very largest models while also using similar methods to perform parameter updates on a modestly-sized LLM with parameter-efficient tuning. We evaluate FIAT's effectiveness on a variety of multilingual tasks and observe that FIAT performs better than both ICL and fine-tuning at scales ranging from 100-10,000 training examples. We hope that FIAT provides a practical way of harnessing the full potential of LLMs without needing to make a hard choice between learning paradigms.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer2024
- QAmeleon: Multilingual QA with Only 5 ExamplesTransactions of the Association for Computational Linguistics, 2023
- Large Language Models Can Self-Improve2023
- XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages2023
- Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes2023
- The Power of Scale for Parameter-Efficient Prompt Tuning2021
- Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference2021
- XOR QA: Cross-lingual Open-Retrieval Question Answering2021
- It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners2021
- TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse LanguagesTransactions of the Association for Computational Linguistics, 2020