Search papers, labs, and topics across Lattice.
City University of Hong Kong
3
0
7
Control-flow hallucination isn't a bug鈥攊t's a feature of probabilistic LLMs, and Agentic Programming offers a robust solution.
Aligning LLM reasoning with a dedicated recommendation head via reinforcement learning yields state-of-the-art recommendation performance in real-world systems.
LLMs can now reliably extract job skills from text, even in low-resource settings, thanks to a novel framework that enforces output validity and reduces hallucinations.
