提出新方法缓解大模型生成与自检不一致的问题
RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models
- 从排序角度定义生成-验证差距，要求答案评分保持一致
- 新方法RankAlign显著缩小差距，优于所有基线
- 效果跨任务和词汇泛化，适合提升模型可靠性
尽管大语言模型在多项任务中表现更强大、更准确，但其行为仍存在一些根本性不可靠性。一个关键问题是，当提示发生变化时，模型对同一信息的表述不一致。本文关注模型生成答案与其自身对该答案的验证之间的差异，即生成-验证差距。我们以比以往更严格的方式定义这一差距：要求生成器与验证器在全部候选答案上的评分具有相关性，即这些答案在正常语言使用中可能出现，且不违背格赖斯准则。实验表明，在问答、词汇语义任务和下一词预测等多种场景下，该差距依然显著存在。为此，我们提出基于排序的训练方法RankAlign，结果证明其能显著缩小差距，超越所有基线方法。此外，该方法在域外任务和词汇上也具有良好泛化能力。
原文摘要 · Abstract (English)
Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information when prompts are changed. In this paper, we consider the discrepancy between a model's generated answer and their own verification of that answer, the generator-validator gap. We define this gap in a more stringent way than prior work: we expect correlation of scores from a generator and a validator over the entire set of candidate answers, i.e., candidate completions that could possibly arise during ordinary language use without breaking Gricean norms. We show that according to this measure, a large gap exists in various settings, including question answering, lexical semantics tasks, and next-word prediction. We then propose RankAlign, a ranking-based training method, and show that it significantly closes the gap, surpassing all baseline methods. Moreover, this approach generalizes well to out-of-domain tasks and lexical items.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。