The Empowerment of Science of Science by Large Language Models: New Tools and Methods

The COMPASS (Context-Modulated PID Attention Steering System) is introduced as a framework designed to mitigate hallucinations in large language models (LLMs). It incorporates a feedback loop within the decoding process, utilizing the Context Reliance Score (CRS) to assess how attention heads utilize contextual evidence. This system aims to ensure factual consistency in generated outputs without the need for retraining or multiple decoding passes.

Large language models (LLMs) often generate confident yet incorrect outputs, necessitating reliable uncertainty quantification. This study introduces information-lift certificates that compare model probabilities to a skeleton baseline, utilizing sub-gamma PAC-Bayes bounds effective under heavy-tailed distributions. The method achieved 77.0% coverage at 2% risk across eight datasets, significantly outperforming entropy-based methods in blocking critical errors, making it practical for real-world applications.

Large language models (LLMs) exhibit label length bias, where labels of varying lengths are treated inconsistently despite normalization efforts. This paper introduces normalized contextual calibration (NCC), a method that normalizes predictions at the full-label level, effectively addressing this bias. NCC demonstrates statistically significant improvements across multiple datasets and models, achieving up to 10% gains in F1 scores. Additionally, it extends bias mitigation to tasks like multiple-choice question answering, showing reduced sensitivity to few-shot example selection.

Andrew Ng, a prominent figure in AI at Google, emphasized the importance of learning to code during an interview at AI Dev 25 in New York. He discussed the future of developers, the significance of responsible AI, and expressed skepticism about the hype surrounding Artificial General Intelligence (AGI). Ng's insights reflect a broader conversation about the evolving role of technology and the skills needed in the AI landscape.