Search papers, labs, and topics across Lattice.
Department of Data Science and Artificial Intelligence (DSAI), Monash University www.ukp.tu-darmstadt.de
2
0
5
Human evaluative claims can significantly enhance the quality of AI-generated peer reviews, striking a crucial balance between automation and accountability.
LLMs struggle to identify relevant legal issues with high precision, but a neuro-symbolic approach using sparse linear models over LLM-generated analytical factors can boost performance by 30-40%.