Assisting humans in complex comparisons: automated information comparison at scale
This addresses the problem of automating complex information comparisons at scale for users across knowledge domains, though it appears incremental as it builds on existing techniques like abstractive summarization and retrieval augmented generation.
The paper tackled the scalability challenges of using Large Language Models for information comparisons by developing the ASC$^2$End system, which employs semantic text similarity and data-handling strategies to automate comparisons, showing desirable results in evaluations.
Generative Large Language Models enable efficient analytics across knowledge domains, rivalling human experts in information comparisons. However, the applications of LLMs for information comparisons face scalability challenges due to the difficulties in maintaining information across large contexts and overcoming model token limitations. To address these challenges, we developed the novel Abstractive Summarization & Criteria-driven Comparison Endpoint (ASC$^2$End) system to automate information comparison at scale. Our system employs Semantic Text Similarity comparisons for generating evidence-supported analyses. We utilize proven data-handling strategies such as abstractive summarization and retrieval augmented generation to overcome token limitations and retain relevant information during model inference. Prompts were designed using zero-shot strategies to contextualize information for improved model reasoning. We evaluated abstractive summarization using ROUGE scoring and assessed the generated comparison quality using survey responses. Models evaluated on the ASC$^2$End system show desirable results providing insights on the expected performance of the system. ASC$^2$End is a novel system and tool that enables accurate, automated information comparison at scale across knowledge domains, overcoming limitations in context length and retrieval.