Papers with Post-training of Large Language Models
Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning (2025.acl-long)
Copied to clipboard
| Challenge: | Results show that supervised fine-tuning and preference finetunation are the most efficient approaches for large language models. |
| Approach: | They propose to use Supervised Finetuning and Preference Finetunes to optimize training data budgets for Large Language Models. |
| Outcome: | The proposed approach improves performance on math tasks by 15% on the most expensive model, 1,000 examples. |
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)
Copied to clipboard
Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang
| Challenge: | achieving data-efficient post-training of Large Language Models is a key research question. |
| Approach: | They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective. |
| Outcome: | The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems. |