Literature Meets Data: A Synergistic Approach to Hypothesis Generation
This work addresses the challenge of improving hypothesis generation for scientific research by synergizing theory and data, offering incremental but measurable gains in AI-assisted decision-making.
The paper tackled the problem of hypothesis generation by developing a method that combines literature-based insights with data using LLMs, demonstrating performance improvements of 8.97% to 15.75% over baselines on five datasets and enhancing human accuracy by 7.44% to 14.19% in deception and AI content detection tasks.
AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in generating novel and plausible hypotheses, it remains an open question whether they can complement each other. To address this, we develop the first method that combines literature-based insights with data to perform LLM-powered hypothesis generation. We apply our method on five different datasets and demonstrate that integrating literature and data outperforms other baselines (8.97\% over few-shot, 15.75\% over literature-based alone, and 3.37\% over data-driven alone). Additionally, we conduct the first human evaluation to assess the utility of LLM-generated hypotheses in assisting human decision-making on two challenging tasks: deception detection and AI generated content detection. Our results show that human accuracy improves significantly by 7.44\% and 14.19\% on these tasks, respectively. These findings suggest that integrating literature-based and data-driven approaches provides a comprehensive and nuanced framework for hypothesis generation and could open new avenues for scientific inquiry.