mlsanityData to 7 Oct 2026

Instruction Fusion: Advancing Prompt Evolution through Hybridization

arXiv 2312.15692 ↗First posted 25 Dec 2023cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

The fine-tuning of Large Language Models (LLMs) specialized in code generation has seen notable advancements through the use of open-domain coding queries. Despite the successes, existing methodologies like Evol-Instruct encounter performance limitations, impeding further enhancements in code generation tasks. This paper examines the constraints of existing prompt evolution techniques and introduces a novel approach, Instruction Fusion (IF). IF innovatively combines two distinct prompts through a hybridization process, thereby enhancing the evolution of training prompts for code LLMs. Our experimental results reveal that the proposed novel method effectively addresses the shortcomings of prior methods, significantly improving the performance of Code LLMs across five code generation benchmarks, namely HumanEval, HumanEval+, MBPP, MBPP+ and MultiPL-E, which underscore the effectiveness of Instruction Fusion in advancing the capabilities of LLMs in code generation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

15 of 26 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  8. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  9. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  10. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  11. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  12. 2023StarCoder: may the source be with you!cited by 790
3 more
  1. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  2. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  3. 2023Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Taskscited by 53

Built on by

Cited by year

Citing papers per year: 2024: 6; 2025: 1.

7 papers.

  1. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  2. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 82
  3. 2024Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuningcited by 9
  4. 2024CSEPrompts: A Benchmark of Introductory Computer Science Promptscited by 3
  5. 2024Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variantscited by 3
  6. 2024TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolutioncited by 0
  7. 2025TopicProphet: Prophesies on Temporal Topic Trends and Stockscited by 0