Search papers, labs, and topics across Lattice.
6
0
6
11
SOGR1 achieves state-of-the-art performance in knowledge graph question answering while being significantly more efficient than larger models.
Negative token filtering enables stable single-rollout training, outperforming traditional group-based methods on agentic tasks while maintaining efficiency.
CroSearch-R1 reveals that integrating cross-lingual knowledge through a dynamic retrieval strategy can substantially enhance the performance of Retrieval-Augmented Generation systems.
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.
Forget full fine-tuning: this dynamic routing strategy lets you adapt dense retrieval to new domains while using just 2% of the parameters.
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.
