SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.12607 · 2022

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

How to usefully encode compositional task structure has long been a core challenge in AI. Recent work in chain of thought prompting has shown that for very large neural language models (LMs), explicitly demonstrating the inferential steps involved in a target task may improve performance over end-to-end learning that focuses on the target task alone. However, chain of thought prompting has significant limitations due to its dependency on huge pretrained LMs. In this work, we present compositional fine-tuning (CFT): an approach based on explicitly decomposing a target task into component tasks, and then fine-tuning smaller LMs on a curriculum of such component tasks. We apply CFT to recommendation tasks in two domains, world travel and local dining, as well as a previously studied inferential task (sports understanding). We show that CFT outperforms end-to-end learning even with equal amounts of data, and gets consistently better as more component tasks are modeled via fine-tuning. Compared with chain of thought prompting, CFT performs at least as well using LMs only 7.4% of the size, and is moreover applicable to task domains for which data are not available during pretraining.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.12607")
get_code_for_paper("2210.12607")
have("2210.12607")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.12607.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.12607.svg)](https://syntology.ai/paper/2210.12607)

Connect an agent — have() is free.