arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06147cs.LGcs.CLstat.ML
收藏

用于文本条件回归的LLM流程

LLM Flow Processes for Text-Conditioned Regression

Secondmind;Wayve

Felix Biggs, Samuel Willis

AI总结:

本文提出结合轻量级神经过程与边际LLM预测,以解决文本条件回归中的误差累积问题,提升预测校准和局部一致性。

摘要:

近期研究表明,预训练的大语言模型(LLM)在回归任务(如时间序列预测)中表现出色,能整合专家先验知识和文本元数据信息。然而,即使在短序列(<100个点)中也存在严重的误差累积问题,且这些模型计算密集且难以并行化。边际LLM预测不受此影响且可轻松并行化,但预测过宽的密度。为此,我们提出将这些密度与轻量级(基于扩散的)神经过程结合,以获得更校准的预测、局部一致的轨迹以及在元学习器中的文本条件函数空间选择。我们还提出一种梯度自由(非蒙特卡洛)方法,用于从评分模型和专家(此处为LLM预测密度)的专家集合的乘积中采样。我们相信此通用方法具有独立价值,适用于任何专家可与高斯函数闭合形式卷积的情况。

英文摘要:

Recent work has demonstrated surprisingly good performance of pre-trained LLMs on regression tasks (for example, time-series prediction), with the ability to incorporate expert prior knowledge and the information contained in textual metadata. However we observe major error cascades even in short sequences < ~100 points; these models are also computationally intensive and difficult to parallelise. Marginal LLM predictions do not suffer this issue and are trivially parallelised, but can predict over-broad densities. To address this, we propose combining these densities with a lightweight (diffusion-based) neural process. We show that this combination leads to better-calibrated predictions overall, outputs locally consistent trajectories, and leads to text-conditioned function space selection in the meta-learner. As part of this work we propose a gradient-free (and non-Monte Carlo) method for sampling from a product-of-experts of a score model and an 'expert' (here the LLM predictive densities). We believe this general method is of independent interest as it is applicable whenever an expert can be convolved with a Gaussian in closed form.

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。

↑