Chapter 1 · 2025
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
Jiaqi Li, Xinyi Dong, Yang Liu
Abstract
We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively generates self-reflection for self-training, fostering a continuous and self-evolving process. Leveraging this pipeline, we construct ReflectEvo-460k, a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks.
Topics
small language modelsmeta introspectionself-reflectionreflection learningself-generated data
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2025
Venue
Type
ChapterCh. 1
Authors3
Zone III Analysis
Related Papers
ReAct: Synergizing Reasoning and Acting in Language Mod…
2023 · Ch.1
Reflexion: Language Agents with Verbal Reinforcement Le…
2023 · Ch.1
Tree of Thoughts: Deliberate Problem Solving with Large…
2023 · Ch.1
Toolformer: Language Models Can Teach Themselves to Use…
2023 · Ch.1
View all Chapter 1 papers →