{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:06:00Z","timestamp":1773803160471,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"28","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Large-scale Chinese spelling correction (CSC) remains critical for real-world text processing, yet existing LLMs and supervised methods lack robustness to novel errors and rely on costly annotations. We introduce CEC-Zero, a zerosupervision reinforcement learning framework that addresses this by enabling LLMs to correct their own mistakes. CEC-Zero synthesizes errorful inputs from clean text, computes cluster-consensus rewards via semantic similarity and candidate agreement, and optimizes the policy with PPO. It outperforms supervised baselines by 10\u201313 F1 points and strong LLM fine-tunes by 5\u20138 points across 9 benchmarks, with theoretical guarantees of unbiased rewards and convergence.CEC-Zero establishes a label-free paradigm for robust, scalable CSC, unlocking LLM potential in noisy text pipelines.<\/jats:p>","DOI":"10.1609\/aaai.v40i28.39534","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:41:33Z","timestamp":1773798093000},"page":"23612-23620","source":"Crossref","is-referenced-by-count":0,"title":["CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards"],"prefix":"10.1609","volume":"40","author":[{"given":"Zhiming","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Canran","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39534\/43495","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39534\/43495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:41:34Z","timestamp":1773798094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"28","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i28.39534","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}