2 papers
cs.LG2026
Learn from A Rationalist: Distilling Intermediate Interpretable Rationales
Jiayi Dai, Randy Goebel
Because of the pervasive use of deep neural networks (DNNs), especially in high-stakes domains, the interpretability of DNNs has received increased attention. The general idea of r…
cs.CL2026
Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
Da Song, Yuheng Huang, Boqi Chen +4
The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory st…