Cascaded Batch Prompting

2026-08-27

AI Summary

该研究针对批量提示方法导致的下游任务性能不稳定问题，提出了一种两阶段的级联批量提示方法，通过分离复杂推理和符号接地来解决此问题。

Abstract

Although batch prompting makes large language model inference more efficient by processing multiple instances simultaneously, it suffers from unpredictable downstream task performance. We propose cascaded batch prompting, a two-stage approach designed to resolve the unpredictability of conventional batch prompting by disentangling complex reasoning from symbol grounding. Experiments on multiple-choice question answering and natural language inference demonstrate that the proposed method outperforms the standard single prompting baseline while achieving a speedup proportional to batch size, establishing a new state of the art on the Pareto frontier.

Problem

• batch prompting
• downstream task performance
• unpredictability

Innovation

• cascaded batch prompting
• complex reasoning
• symbol grounding
• downstream task performance