Search papers, labs, and topics across Lattice.
3
3
5
12
Answer-conditioning can undermine reasoning accuracy in LLMs, leading to a staggering 27-point drop on difficult tasks.
Stop relying on flat chunks: Hierarchical document parsing boosts retrieval recall by 12.9% and QA accuracy by 6.8% in open-domain QA.
Synthetically corrupting data with a taxonomy of OCR errors lets you train LLMs to fix real-world OCR mistakes and dramatically improve document understanding.
