2 papers
cs.CL2026
GRACE: Grounded Adversarial Reasoning over Canadian Law
Jiakang Xu, Wantong Huo, Udom Silparcha +1
Large language models have shown strong performance across a range of legal tasks, but existing benchmarks rarely evaluate the ability to take and defend a legal position, reason u…
cs.CL2026
Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA
Sterling Huang, Abigayle Brown, Jiyoo Noh +4
Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines wheth…