Shu Wang
4 papers · Latest:
Natural Language Processing
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a new benchmark for abstract question answering over documents, providing robust evaluation for coverage, hallucination, and retrieval scope.
2605.10168
SPHEREx Ultracool Dwarf spectral Atlas (SUDA): Atmospheric and Fundamental Parameters of Ultracool Dwarfs
SUDA presents a new spectral atlas of 1675 ultracool dwarfs, deriving atmospheric and fundamental parameters and revealing spectral trends.
2604.26771
Galaxies & CosmologyCan BLR line profile shape improve single-epoch black hole mass estimates?
This paper finds marginal evidence that broad-line region (BLR) profile shape correlates with the virial coefficient, potentially improving black hole mass estimates.
2604.24901
General EconomicsUnderstanding the Mechanism of Altruism in Large Language Models
Researchers uncover the neural mechanisms of altruism in LLMs using SAEs, identifying and manipulating features linked to prosocial behavior.
2604.19260
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.