{"labels":{"en":"Delayed Convergence and Emergent CoT Reliance in RL-Tuned Language Models"},"descriptions":{"en":"scientific paper published in CEUR-WS Volume 4259"},"claims":{"P31":"Q13442814","P1433":"Q141603316","P1476":{"text":"Delayed Convergence and Emergent CoT Reliance in RL-Tuned Language Models","language":"en"},"P407":"Q1860","P953":"https://ceur-ws.org/Vol-4259/paper13.pdf","P50":[],"P2093":[{"value":"Pablo Pérez-Lázaro","qualifiers":{"P1545":"1"}},{"value":"Rocío Aznar-Gimeno","qualifiers":{"P1545":"2"}},{"value":"Francisco José Lacueva-Pérez","qualifiers":{"P1545":"3"}},{"value":"Paula Peña-Larena","qualifiers":{"P1545":"4"}},{"value":"Rafael del-Hoyo-Alonso","qualifiers":{"P1545":"5"}}]}}