Search papers, labs, and topics across Lattice.
HiTZ Center -Ixa, Sistemas de Di谩logo, Generaci贸n de Lenguaje Natural, University of the Basque Country UPV/EHU, Apren- dizaje No Supervisado
2
0
4
Fine-tuned 8B models can outperform 70B counterparts in reasoning and tool use, challenging assumptions about model size superiority.
LLMs can achieve state-of-the-art coreference resolution in task-based dialogue by reasoning over object metadata at test time, even outperforming supervised methods in cross-domain generalization.
