arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.09714stat.MLcs.LGstat.ME
收藏

通过增强共形预测方法实现大语言模型的有效性

Large language model validity via enhanced conformal prediction methods

Stanford University(斯坦福大学)

John J. Cherian, Isaac Gibbs, Emmanuel J. Candès

AI总结:

针对现有共形语言建模方法保证无条有效性、易误删有效主张的问题,提出两种增强共形预测方法,推广条件共形流程并优化评分函数,在传记和医疗问答数据集验证了有效性,为LLM输出提供更可靠的有效性保证。

摘要:

我们开发了新的共形推断方法,用于为大语言模型(LLM)的输出提供有效性保证。共形语言建模领域的现有工作会识别文本的一个子集,该子集满足正确性的高概率保证。这些方法的工作原理是:若在某个主张上计算的评分函数未能超过通过拆分共形预测校准的阈值,就从LLM的原始回复中过滤掉该主张。该领域的现有方法存在两个缺陷。第一,其所声明的保证不具备条件有效性,过滤步骤的可信度可能会根据回复的主题而变化。第二,由于评分函数并不完美,过滤步骤可能会移除许多有价值且准确的主张。我们通过两种新的共形方法解决了这两个挑战。首先,我们推广了Gibbs等人(2023)提出的条件共形流程,以便在需要保留输出效用时,自适应地给出更弱的保证。其次,我们展示了如何通过一种可对条件共形流程进行求导的新型算法,系统性地提升评分函数的质量。我们在传记类和医疗问答数据集上验证了所提方法的有效性。

英文摘要:

We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs). Prior work in conformal language modeling identifies a subset of the text that satisfies a high-probability guarantee of correctness. These methods work by filtering claims from the LLM's original response if a scoring function evaluated on the claim fails to exceed a threshold calibrated via split conformal prediction. Existing methods in this area suffer from two deficiencies. First, the guarantee stated is not conditionally valid. The trustworthiness of the filtering step may vary based on the topic of the response. Second, because the scoring function is imperfect, the filtering step can remove many valuable and accurate claims. We address both of these challenges via two new conformal methods. First, we generalize the conditional conformal procedure of Gibbs et al. (2023) in order to adaptively issue weaker guarantees when they are required to preserve the utility of the output. Second, we show how to systematically improve the quality of the scoring function via a novel algorithm for differentiating through the conditional conformal procedure. We demonstrate the efficacy of our approach on biography and medical question-answering datasets.

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。

↑