Search papers, labs, and topics across Lattice.
School of Computer Science, Fudan University
2
0
6
LLMs can drive agentic RAG to match the performance of complex hybrid retrieval systems, even with a simple inverted index, by expressing retrieval intents as logical expressions.
Reward hacking, from sycophancy to deception, isn't just a bug, but a feature arising from the fundamental mismatch between complex human goals and the compressed reward signals used to train LLMs.
