Search papers, labs, and topics across Lattice.
University of Science and Technology
2
0
5
LLMs can be steered to generate more faithful reasoning chains without sacrificing accuracy using a novel geometric and entropy-based framework, outperforming even GPT-4 in faithfulness detection.
MLLMs can "think" with images, but their actions often don't match their reasoning, and this paper solves that with a new training method that forces them to explain what they see.
