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

arXiv: https://arxiv.org/abs/2210.12607 · HTML: https://mlsanity.com/paper/2210.12607/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 23 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation](https://mlsanity.com/paper/2007.15356/) (2020)
- [Adversarial Generation of Natural Language](https://mlsanity.com/paper/1705.10929/) (2017)
- [Hey AI, Can You Solve Complex Tasks by Talking to Agents?](https://mlsanity.com/paper/2110.08542/) (2021)
- ["It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems](https://mlsanity.com/paper/2109.07576/) (2021)

## Built on by (most cited first, 10 of 10)

- [Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings](https://mlsanity.com/paper/2308.02575/) (2023)
- [Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows](https://mlsanity.com/paper/2312.11681/) (2023)
- [Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflow](https://mlsanity.com/paper/2402.09894/) (2024)
- [V-RECS, a Low-Cost LLM4VIS Recommender with Explanations, Captioning and Suggestions](https://mlsanity.com/paper/2406.15259/) (2024)
- [CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs](https://mlsanity.com/paper/2311.17376/) (2023)
- [SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version](https://mlsanity.com/paper/2508.15478/) (2025)
- [FeedQUAC: Quick Unobtrusive AI-Generated Commentary](https://mlsanity.com/paper/2504.16416/) (2025)
- [DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization](https://mlsanity.com/paper/2406.04669/) (2024)
- [E.A.R.T.H.: Structuring Creative Evolution through Model Error in Generative AI](https://mlsanity.com/paper/2507.18004/) (2025)
- [Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction](https://mlsanity.com/paper/2508.19359/) (2025)

## Abstract (arXiv)

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.