4 papers
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…
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…
Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey
Weixu Zhang, Yifei Wang, Yuanfeng Song +6
The emergence of natural language processing has revolutionized the way users interact with tabular data, enabling a shift from traditional query languages and manual plotting to m…
Detection and Amelioration of Social Engineering Vulnerability in Contingency Table Data using an Orthogonalised Log-linear Analysis
Glynn Rogers, Malcolm Crompton, Gaurav Sapre +1
Social Engineering has emerged as a significant threat in cyber security. In a dialog based attack, by having enough of a potential victim's personal data to be convincing, a socia…