Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
2
Experiments on SemEval-2017 and WebPun show that PunGraph consistently improves the performance of small-scale LLMs and achieves competitive results against strong proprietary models, highlighting the benefits of integrating structured knowledge with LLMs.
LLMs can get up to 6x more logically consistent without human feedback, simply by fusing NLI scores into the DPO training loop.
LALMs still struggle to get the joke, with a new benchmark showing they can't reliably recognize, locate, or understand audio puns.
