ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
This work addresses the problem of labor-intensive and time-consuming text evaluation for researchers and practitioners in natural language processing, offering an incremental improvement over existing LLM-based evaluators.
The paper tackles the challenge of improving LLM-based text evaluation by proposing ChatEval, a multi-agent debate framework that moves beyond single-agent approaches to mimic human collaborative evaluation processes, resulting in enhanced reliability and effectiveness in assessing generated responses on open-ended questions and NLG tasks.
Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost. With the emergence of large language models (LLMs), researchers have explored LLMs' potential as alternatives for human evaluation. While these single-agent-based approaches show promise, experimental results suggest that further advancements are needed to bridge the gap between their current effectiveness and human-level evaluation quality. Recognizing that best practices of human evaluation processes often involve multiple human annotators collaborating in the evaluation, we resort to a multi-agent debate framework, moving beyond single-agent prompting strategies. The multi-agent-based approach enables a group of LLMs to synergize with an array of intelligent counterparts, harnessing their distinct capabilities and expertise to enhance efficiency and effectiveness in handling intricate tasks. In this paper, we construct a multi-agent referee team called ChatEval to autonomously discuss and evaluate the quality of generated responses from different models on open-ended questions and traditional natural language generation (NLG) tasks. Our analysis shows that ChatEval transcends mere textual scoring, offering a human-mimicking evaluation process for reliable assessments. Our code is available at https://github.com/chanchimin/ChatEval.