 A Survey on Efficient Large Language Model Training: From Data-centric PerspectivesAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-ReflectionAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided SamplingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
