Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions
This addresses the challenge of reducing reliance on human-annotated data for agreement-finding tasks in AI systems, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of finding agreement among diverse opinions in multiagent systems by proposing Self-Agreement, a framework that fine-tunes LLMs using self-generated data, achieving comparable performance to GPT-3 with only 1/25 of its parameters.
Finding an agreement among diverse opinions is a challenging topic in multiagent systems. Recently, large language models (LLMs) have shown great potential in addressing this challenge due to their remarkable capabilities in comprehending human opinions and generating human-like text. However, they typically rely on extensive human-annotated data. In this paper, we propose Self-Agreement, a novel framework for fine-tuning LLMs to autonomously find agreement using data generated by LLM itself. Specifically, our approach employs the generative pre-trained transformer-3 (GPT-3) to generate multiple opinions for each question in a question dataset and create several agreement candidates among these opinions. Then, a bidirectional encoder representations from transformers (BERT)-based model evaluates the agreement score of each agreement candidate and selects the one with the highest agreement score. This process yields a dataset of question-opinion-agreements, which we use to fine-tune a pre-trained LLM for discovering agreements among diverse opinions. Remarkably, a pre-trained LLM fine-tuned by our Self-Agreement framework achieves comparable performance to GPT-3 with only 1/25 of its parameters, showcasing its ability to identify agreement among various opinions without the need for human-annotated data.