Search papers, labs, and topics across Lattice.
2
0
4
1
On-policy reward modeling with LLM judges not only unlocks significant performance gains on complex mathematical reasoning tasks, but also generalizes to improve performance on simpler numerical and multiple-choice benchmarks.
Forget prompt engineering – LSE trains LLMs to self-edit their own contexts at test time, outperforming even GPT-5 and Claude Sonnet 4.5 in Text-to-SQL and question answering.
