Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
1
3
2
LLMs can mimic human lexical patterns, but larger models act like stereotypical humans, sacrificing diversity for typicality in word associations, a trade-off tunable by temperature.
Despite the rise of LLMs, unsupervised word sense induction remains an open problem, with even advanced models failing to beat a naive baseline.