{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:56:31Z","timestamp":1782910591179,"version":"3.54.5"},"publisher-location":"Stroudsburg, PA, USA","reference-count":0,"publisher":"Association for Computational Linguistics","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.18653\/v1\/2026.findings-acl.865","type":"proceedings-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:25:50Z","timestamp":1782908750000},"page":"17472-17489","source":"Crossref","is-referenced-by-count":0,"title":["SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models"],"prefix":"10.18653","author":[{"given":"Yifu","family":"Huo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunjie","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peinan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongran","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaozhi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian Hua","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Changxiaojia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JingBo","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1643","event":{"name":"Findings of the Association for Computational Linguistics: ACL 2026","location":"San Diego, California, United States","start":{"date-parts":[[2026,7]]},"end":{"date-parts":[[2026,7]]}},"container-title":["Findings of the Association for Computational Linguistics: ACL 2026"],"original-title":[],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:41:36Z","timestamp":1782909696000},"score":1,"resource":{"primary":{"URL":"https:\/\/aclanthology.org\/2026.findings-acl.865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.18653\/v1\/2026.findings-acl.865","relation":{},"subject":[],"published":{"date-parts":[[2026]]}}}