2 papers
cs.CL2026
AI Can Learn Scientific Taste
Jingqi Tong, Mingzhe Li, Hangcheng Li +20
Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with the potential for long-term sci…
cs.CL2025
Unified Enhancement of the Generalization and Robustness of Language Models via Bi-Stage Optimization
Yudao Sun, Juan Yin, Juan Zhao +3
Neural network language models (LMs) are confronted with significant challenges in generalization and robustness. Currently, many studies focus on improving either generalization o…