Ori Press(@ori_press):LMs can play chess, but they can't really explain their moves well (chess engines can't at all). Our new BinProp scaffold tackles this, and nearly triples LMs’ score on our chess-explanation benchmark. It works on other games too! Try it on your own games on our site-🧵👇

Ori Press

@ori_press

ML Researcher @nebiusai PhD from @bethgelab

가입 December 2018

445 팔로잉 중 608 팬

Ori Press@ori_press

2026.10.14 13:58

LMs can play chess, but they can't really explain their moves well (chess engines can't at all). Our new BinProp scaffold tackles this, and nearly triples LMs’ score on our chess-explanation benchmark. It works on other games too! Try it on your own games on our site-🧵👇