# PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching

arXiv: https://arxiv.org/abs/2312.05621 · HTML: https://mlsanity.com/paper/2312.05621/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 9 Dec 2023.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Recent Advances in Reinforcement Learning in Finance](https://mlsanity.com/paper/2112.04553/) (2021)
- [One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2306.07967/) (2023)
- [Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes](https://mlsanity.com/paper/2201.12569/) (2022)

## Built on by (most cited first, 6 of 6)

- [Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration](https://mlsanity.com/paper/2406.15765/) (2024)
- [A Survey on LoRA of Large Language Models](https://mlsanity.com/paper/2407.11046/) (2024)
- [Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors](https://mlsanity.com/paper/2504.04785/) (2025)
- [MBIAS: Mitigating Bias in Large Language Models While Retaining Context](https://mlsanity.com/paper/2405.11290/) (2024)
- [TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains](https://mlsanity.com/paper/2410.11507/) (2024)
- [GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning](https://mlsanity.com/paper/2411.14479/) (2024)

## Abstract (arXiv)

Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment by individuals or small-scale entities. Recently, Low-Rank Adaptation (LoRA) has become a promising alternative, offering high capabilities on par with full tuning with reduced resource overhead. However, attaining satisfactory performance through the fine-tuning of LoRA is a non-trivial challenge. In this paper, we propose PILLOW, which aims to improve LoRA's performance by a discrimination-based prompting method, leveraging LLMs' In-Context Learning ability. PILLOW incorporates a matching network that selects prompts from a user-defined prompt pool, concatenates the selected prompts with the user instruction as input, and performs inference using the LoRA-fine-tuned LLMs. Trained with Reinforcement Learning, PILLOW exhibits commensurate performance on various evaluation metrics compared with typical instruction fine-tuning methods, utilizing only consumer-grade GPU resources and exhibiting a large reduction in computational costs.