Saved in:
Bibliographic Details
Main Authors: Kim, Woo-Chan, Park, Ji-Hoon, Lee, Seong-Whan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.13666
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913948577562624
author Kim, Woo-Chan
Park, Ji-Hoon
Lee, Seong-Whan
author_facet Kim, Woo-Chan
Park, Ji-Hoon
Lee, Seong-Whan
contents Large language models (LLMs) have demonstrated state-of-the-art performance across a wide range of natural language processing tasks. However, high-performing models are typically accessible only via APIs, incurring substantial inference costs. Cascade methods address this by initially employing a cheaper model and escalating to a stronger one only when necessary. Nevertheless, existing cascade approaches struggle to select a reliable representative response and assess the overall reliability of free-form outputs, as they rely on exact text matching. To overcome these limitations, we propose Keyword-inspired Cascade (KiC), a novel framework for cost-efficient free-form text generation. KiC identifies the most representative answer among multiple outputs from a weaker model and evaluates the semantic alignment of other responses with it. Based on the degree of alignment, KiC determines whether to accept the weaker model's output or escalate to a stronger model. Experiments on three free-form text generation benchmarks show that KiC achieves 97.53 percent of GPT-4's accuracy while reducing API costs by 28.81 percent on average, and even outperforms GPT-4 in a specific benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13666
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KiC: Keyword-inspired Cascade for Cost-Efficient Text Generation with LLMs
Kim, Woo-Chan
Park, Ji-Hoon
Lee, Seong-Whan
Computation and Language
Large language models (LLMs) have demonstrated state-of-the-art performance across a wide range of natural language processing tasks. However, high-performing models are typically accessible only via APIs, incurring substantial inference costs. Cascade methods address this by initially employing a cheaper model and escalating to a stronger one only when necessary. Nevertheless, existing cascade approaches struggle to select a reliable representative response and assess the overall reliability of free-form outputs, as they rely on exact text matching. To overcome these limitations, we propose Keyword-inspired Cascade (KiC), a novel framework for cost-efficient free-form text generation. KiC identifies the most representative answer among multiple outputs from a weaker model and evaluates the semantic alignment of other responses with it. Based on the degree of alignment, KiC determines whether to accept the weaker model's output or escalate to a stronger model. Experiments on three free-form text generation benchmarks show that KiC achieves 97.53 percent of GPT-4's accuracy while reducing API costs by 28.81 percent on average, and even outperforms GPT-4 in a specific benchmark.
title KiC: Keyword-inspired Cascade for Cost-Efficient Text Generation with LLMs
topic Computation and Language
url https://arxiv.org/abs/2507.13666