Search papers, labs, and topics across Lattice.
University of Montreal
4
0
6
18
SOGR1 achieves state-of-the-art performance in knowledge graph question answering while being significantly more efficient than larger models.
LLMs re-rank documents better when you learn to route each query to the specific attention heads that matter, instead of relying on static subsets or everything at once.
Attention-based re-ranking gets a boost: ReAttn's post-hoc re-weighting tames over-concentration and lexical bias, leading to more accurate and interpretable results without extra training.
LLMs struggle to balance rational financial decisions with mimicking noisy user behavior, often overfitting to short-term market trends instead of aligning with long-term investment goals.
