METEOR: Evolutionary Journey of Large Language Models from Guidance to Self-Growth
Not on the map. Why?
Abstract (arXiv)
Model evolution enables learning from feedback to refine experiences and update skills, transforming models from having no domain knowledge to becoming domain experts. However, there is currently no unified and effective method for guiding this evolutionary process. To address this gap, we propose the Meteor method, which includes three training phases: weak-to-strong data distillation, iterative training, and self-evolution strategies. Each phase maximizes the model's inherent domain capabilities, allowing it to autonomously refine its domain knowledge and enhance performance. Experiments demonstrate that our approach significantly improves accuracy, completeness, relevance, coherence, and reliability across domain-specific tasks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 18 Nov 2024.
Builds on
28 of 42 references.
References · 28
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
- 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
- 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
- 2023BloombergGPT: A Large Language Model for Financecited by 923
- 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
- 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Modelscited by 325
- 2017Beam Search Strategies for Neural Machine Translationcited by 232
16 more
- 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 211
- 2023TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIscited by 184
- 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
- 2023Large Language Models in Law: A Surveycited by 128
- 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environmentscited by 120
- 2023GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Informationcited by 115
- 2023XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameterscited by 92
- 2023EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Educationcited by 80
- 2023ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agentcited by 78
- 2023FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasetscited by 68
- 2023Memory Augmented Large Language Models are Computationally Universalcited by 45
- 2023OWL: A Large Language Model for IT Operationscited by 43
- 2024Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talkcited by 34
- 2023Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformerscited by 32
- 2023GeoGalactica: A Scientific Large Language Model in Geosciencecited by 32
- 2023HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Promptingcited by 11
Built on by
Citing papers per year: 2026: 1.
1 paper.