Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
6
Language models can now self-select relevant context, slashing attention costs by over 50% while maintaining performance.
PLC-DPO is proposed to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case, which reframes noisy preference learning as actively correcting supervision direction and strength rather than merely filtering suspicious examples.
Static prompts in RL training can hinder performance, but LLM-as-a-Tutor dynamically adapts them to match policy capabilities, leading to superior outcomes.
