# CERET: Cost-Effective Extrinsic Refinement for Text Generation

Source: [CERET: Cost-Effective Extrinsic Refinement for Text Generation](<https://www.sota2.com/research/paper/68fa75901e209131cea68a7f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:36:51.485Z

Authors: Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour

Published: 2024-06-08T22:17:52.000Z

## Abstract

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality typically involve LLM self-improvement / self-reflection that incorporate feedback from models themselves. Despite their effectiveness, these methods are hindered by their high computational cost and lack of scalability. In this work, we propose CERET, a method for refining text generations by considering semantic stability, entailment and inter-sample uncertainty measures. Experimental results show that CERET outperforms Self-consistency and Self-rerank baselines consistently under various task setups, by ~1.6% in Rouge-1 for abstractive summarization and ~3.5% in hit rate for question answering. Compared to LLM Self-rerank method, our approach only requires 9.4% of its latency and is more cost-effective.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.05588>)

[PDF](<https://arxiv.org/pdf/2406.05588.pdf>)
