Search papers, labs, and topics across Lattice.
2
0
6
0
This work identifies a factual-salient layer span within LLMs whose derived signal is selectively elevated for factual tokens and exhibits anomalous spikes at hallucination-prone steps, and proposes DescaPE, a decoding framework that leverages internal model signals to suppress hallucination-prone trajectories at inference time.
Forget hand-annotated visual reasoning datasets: VG-CoT leverages a fully automated pipeline to generate grounded, step-by-step reasoning, enabling scalable and cost-efficient training of more trustworthy LVLMs.
