# Cascaded Batch Prompting

arXiv: https://arxiv.org/abs/2608.27038 · HTML: https://mlsanity.com/paper/2608.27038/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://mlsanity.com/paper/2502.14127/) (2025)

## Built on by (most cited first, 1 of 1)

- [SCBO: Semantically Coherent Batching and Ordering for LLM-Based Social Surveys](https://mlsanity.com/paper/2609.35250/) (2026)

## Abstract (arXiv)

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.