PretrainRL: 缓解大语言模型在开始阶段的事实性幻觉
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
AI总结：
PretrainRL通过在预训练阶段引入强化学习，缓解大语言模型在开始阶段的事实性幻觉问题，通过去偏见和学习机制提升事实准确性。
摘要：
大语言模型（LLMs）尽管具有强大的能力，但仍存在事实性幻觉问题，即生成可验证的虚假信息。我们发现这一问题的根本原因在于预训练语料库中的数据分布不平衡，导致一种
英文摘要：
Large language models (LLMs), despite their powerful capabilities, suffer from factual hallucinations where they generate verifiable falsehoods. We identify a root of this issue: the imbalanced data distribution in the pretraining corpus, which leads to a state of "low-probability truth" and "high-probability falsehood". Recent approaches, such as teaching models to say "I don't know" or post-hoc knowledge editing, either evade the problem or face catastrophic forgetting. To address this issue from its root, we propose \textbf{PretrainRL}, a novel framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. The core principle of PretrainRL is "\textbf{debiasing then learning}." It actively reshapes the model's probability distribution by down-weighting high-probability falsehoods, thereby making "room" for low-probability truths to be learned effectively. To enable this, we design an efficient negative sampling strategy to discover these high-probability falsehoods and introduce novel metrics to evaluate the model's probabilistic state concerning factual knowledge. Extensive experiments on three public benchmarks demonstrate that PretrainRL significantly alleviates factual hallucinations and outperforms state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
