DEBATE: Devil's Advocate-Based Assessment and Text Evaluation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Alex, Kim, Keonwoo, Yoon, Sangwon
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913360881123328
author Kim, Alex
Kim, Keonwoo
Yoon, Sangwon
author_facet Kim, Alex
Kim, Keonwoo
Yoon, Sangwon
contents As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as reference-free metrics, demonstrating their capability to adeptly handle novel tasks. However, these models generally rely on a single-agent approach, which, we argue, introduces an inherent limit to their performance. This is because there exist biases in LLM agent's responses, including preferences for certain text structure or content. In this work, we propose DEBATE, an NLG evaluation framework based on multi-agent scoring system augmented with a concept of Devil's Advocate. Within the framework, one agent is instructed to criticize other agents' arguments, potentially resolving the bias in LLM agent's answers. DEBATE substantially outperforms the previous state-of-the-art methods in two meta-evaluation benchmarks in NLG evaluation, SummEval and TopicalChat. We also show that the extensiveness of debates among agents and the persona of an agent can influence the performance of evaluators.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09935
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DEBATE: Devil's Advocate-Based Assessment and Text Evaluation
Kim, Alex
Kim, Keonwoo
Yoon, Sangwon
Computation and Language
Artificial Intelligence
As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that operate as reference-free metrics, demonstrating their capability to adeptly handle novel tasks. However, these models generally rely on a single-agent approach, which, we argue, introduces an inherent limit to their performance. This is because there exist biases in LLM agent's responses, including preferences for certain text structure or content. In this work, we propose DEBATE, an NLG evaluation framework based on multi-agent scoring system augmented with a concept of Devil's Advocate. Within the framework, one agent is instructed to criticize other agents' arguments, potentially resolving the bias in LLM agent's answers. DEBATE substantially outperforms the previous state-of-the-art methods in two meta-evaluation benchmarks in NLG evaluation, SummEval and TopicalChat. We also show that the extensiveness of debates among agents and the persona of an agent can influence the performance of evaluators.
title DEBATE: Devil's Advocate-Based Assessment and Text Evaluation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.09935