Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
A hybrid model that combines generative and discriminative approaches achieves a remarkable 70.7% detection accuracy while significantly improving calibration in hallucination detection for LVLMs.
Achieving near-optimal accuracy while slashing costs, this cascaded framework ensures only the toughest queries hit the expensive models.
Routing across independently trained LLMs can outperform even the most powerful individual models by strategically leveraging specialized capabilities, but only if you can navigate the complex trade-offs.
