# GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning

arXiv: https://arxiv.org/abs/2411.14479 · HTML: https://mlsanity.com/paper/2411.14479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

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

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Compositional Exemplars for In-context Learning](https://mlsanity.com/paper/2302.05698/) (2023)
- [Unified Demonstration Retriever for In-Context Learning](https://mlsanity.com/paper/2305.04320/) (2023)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [In-context Learning with Retrieved Demonstrations for Language Models: A Survey](https://mlsanity.com/paper/2401.11624/) (2024)
- [Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration](https://mlsanity.com/paper/2212.02216/) (2022)
- [An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration](https://mlsanity.com/paper/2402.04978/) (2024)
- [STaCK: Sentence Ordering with Temporal Commonsense Knowledge](https://mlsanity.com/paper/2109.02247/) (2021)
- [Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction](https://mlsanity.com/paper/2402.13741/) (2024)
- [PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching](https://mlsanity.com/paper/2312.05621/) (2023)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive success in a wide range of natural language processing (NLP) tasks due to their extensive general knowledge of the world. Recent works discovered that the performance of LLMs is heavily dependent on the input prompt. However, prompt engineering is usually done manually in a trial-and-error fashion, which can be labor-intensive and challenging in order to find the optimal prompts. To address these problems and unleash the utmost potential of LLMs, we propose a novel LLMs-agnostic framework for prompt optimization, namely GRL-Prompt, which aims to automatically construct optimal prompts via reinforcement learning (RL) in an end-to-end manner. To provide structured action/state representation for optimizing prompts, we construct a knowledge graph (KG) that better encodes the correlation between the user query and candidate in-context examples. Furthermore, a policy network is formulated to generate the optimal action by selecting a set of in-context examples in a rewardable order to construct the prompt. Additionally, the embedding-based reward shaping is utilized to stabilize the RL training process. The experimental results show that GRL-Prompt outperforms recent state-of-the-art methods, achieving an average increase of 0.10 in ROUGE-1, 0.07 in ROUGE-2, 0.07 in ROUGE-L, and 0.05 in BLEU.