# Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

> Research article (Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023) · cited 27× · AI/ML

**Wikidata**: [openalex:W4389519109](https://www.wikidata.org/wiki/openalex:W4389519109)  
**Source**: https://4ort.xyz/entity/evaluation-metrics-in-the-era-of-gpt-4-reliably-evaluating-large-language-models-on-sequence-to-sequence-tasks