Search papers, labs, and topics across Lattice.
Institute of Software, Chinese Academy of Sciences
3
0
6
4
Bash-Commenter achieves a remarkable 33.40% BLEU-4 score, setting a new benchmark for automated comment generation in Bash scripting.
Forget struggling with cryptic SQL: a new LLM fine-tuned with human preferences generates comments so good, they beat Qwen3-14B by up to 13% on standard metrics.
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.
