Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
Authors:
- Li ChenglinLCLi Chenglin
- Qianglong ChenQCQianglong Chen
- Zhi LiZLZhi Li
- FengTao FengTaoFFFengTao FengTao
- Yicheng LiYLYicheng Li
- Fei YuFYFei Yu
- Yin ZhangYZYin Zhang
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 1707-1721
Abstract
Li Chenglin, Qianglong Chen, Zhi Li, FengTao FengTao, Yicheng Li, Hao Chen, Fei Yu, Yin Zhang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.Keywords
This publication has 9 references indexed in Scilit:
- Instruction Tuning for Large Language Models: A SurveyACM Computing Surveys, 2026
- A Survey on Data Selection for LLM Instruction TuningJournal of Artificial Intelligence Research, 2025
- Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment2024
- AlphaMath Almost Zero: Process Supervision without Process2024
- Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing2024
- When is Tree Search Useful for LLM Planning? It Depends on the Discriminator2024
- Prompt-Based Monte-Carlo Tree Search for Goal-oriented Dialogue Policy Planning2023
- Reasoning with Language Model is Planning with World Model2023
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023