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 2403.04182cs.CLcs.AI
收藏

面向大语言模型的回归感知推理

Regression-aware Inference with LLMs

Google Research(谷歌研究院)

Michal Lukasik, Harikrishna Narasimhan, Aditya Krishna Menon, Felix Yu, Sanjiv Kumar

AI总结:

针对大语言模型自回归采样推理在回归与评分任务指标上非最优的问题,提出基于最小贝叶斯风险解码的回归感知推理策略,可从采样响应中闭式估计贝叶斯最优解,在多数据集和模型上显著优于基线。

摘要:

大语言模型(LLM)已在包括回归与评分任务在内的诸多应用中展现出优异性能。通常,人们通过从模型输出分布中进行自回归采样来获取LLM的输出。我们研究发现,这种推理策略对于常用的回归与评分评估指标而言并非最优。作为解决方案,我们基于最小贝叶斯风险解码的已有研究,提出了替代推理策略,该策略可从采样响应中以闭式解形式估计回归与评分指标的贝叶斯最优解。实验表明,我们的方案在多个数据集和模型上均显著优于基线方法。

英文摘要:

Large language models (LLMs) have shown strong results on a range of applications, including regression and scoring tasks. Typically, one obtains outputs from an LLM via autoregressive sampling from the model's output distribution. We show that this inference strategy can be sub-optimal for common regression and scoring evaluation metrics. As a remedy, we build on prior work on Minimum Bayes Risk decoding, and propose alternate inference strategies that estimate the Bayes-optimal solution for regression and scoring metrics in closed-form from sampled responses. We show that our proposal significantly improves over baselines across datasets and models.

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。

↑