Large language models (LLMs) often necessitate extensive labeled datasets and
training compute to achieve impressive performance across downstream tasks.
This paper explores a self-training paradigm, where the LLM autonomously
curates its own labels and selectively trains on unknown data samples
identified through a reference-free consistency method. Empirical evaluations
demonstrate significant improvements in reducing hallucination in generation
across multiple subjects. Furthermore, the selective training framework
mitigates catastrophic forgetting in out-of-distribution benchmarks, addressing
a critical limitation in training LLMs. Our findings suggest that such an
approach can substantially reduce the dependency on large labeled datasets,
paving the way for more scalable and cost-effective language model training.

该论文研究自训练范式，其中大型语言模型 (Large language models, LLMs) 通过自主策划标签并选择性地在未知数据样本上训练，以显著改善多个主题中生成中的虚构问题。此外，选择性训练框架在处理超出分布基准的灾难性遗忘时具有重要意义，解决了训练 LLMs 过程中的关键限制。我们的研究结果表明，这种方法可以大幅减少对大规模标记数据的依赖，为更可伸缩和经济有效的语言模型训练铺平了道路。