Search papers, labs, and topics across Lattice.
Affiliation:
3
0
2
XTC boosts creative generation diversity by up to 38% while slashing repetition by 71%, all without sacrificing fluency.
DRY cuts verbatim looping by nearly half without sacrificing performance, revolutionizing how we approach text generation in LLMs.
As reasoning complexity increases, LLMs show a striking accuracy drop, with performance plummeting from 30.6% to just 17.6% as inferential steps rise from one to four.
