{"id":"https://openalex.org/W7204815970","doi":"https://doi.org/10.18653/2026.findings-emnlp.1599","title":"A Survey on Rubric-guided Reinforcement Learning for Language Models","display_name":"A Survey on Rubric-guided Reinforcement Learning for Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204815970","doi":"https://doi.org/10.18653/2026.findings-emnlp.1599"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1599","doi":"https://doi.org/10.18653/2026.findings-emnlp.1599","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1599","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1599.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1599.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074064317","display_name":"Zifei Shan","orcid":"https://orcid.org/0000-0002-8283-6498","observed_orcids":["https://orcid.org/0000-0002-8283-6498"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zifei Shan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148819775","display_name":"Fangning Shao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangning Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8716,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9708115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"34065","last_page":"34087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.35280001163482666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.35280001163482666,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19249999523162842,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16529999673366547,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.9700000286102295},{"id":"https://openalex.org/keywords/large-language-model-alignment","display_name":"large language model alignment","score":0.8529999852180481},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.6370000243186951},{"id":"https://openalex.org/keywords/constitution","display_name":"constitution","score":0.7039999961853027},{"id":"https://openalex.org/keywords/multimodal-alignment","display_name":"multimodal alignment","score":0.9049999713897705},{"id":"https://openalex.org/keywords/reward-hacking","display_name":"reward hacking","score":0.9039999842643738},{"id":"https://openalex.org/keywords/semantic-drift","display_name":"semantic drift","score":0.9359999895095825}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8059999942779541},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6991999745368958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6726999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565999746322632},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1599","doi":"https://doi.org/10.18653/2026.findings-emnlp.1599","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1599","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1599.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.27505","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27505","pdf_url":"https://arxiv.org/pdf/2608.27505","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27505","doi":"https://doi.org/10.48550/arxiv.2608.27505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27505","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1599","doi":"https://doi.org/10.18653/2026.findings-emnlp.1599","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1599","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1599.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204815970.pdf","grobid_xml":"https://content.openalex.org/works/W7204815970.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W4311991106","https://openalex.org/W4377121527","https://openalex.org/W4384111857","https://openalex.org/W4387635896","https://openalex.org/W4391631327","https://openalex.org/W4395065873","https://openalex.org/W4403746689","https://openalex.org/W4412505606","https://openalex.org/W4414281281","https://openalex.org/W4414815108","https://openalex.org/W4414939355","https://openalex.org/W4416189150","https://openalex.org/W4416401424","https://openalex.org/W7077044503","https://openalex.org/W7103170635","https://openalex.org/W7116876396","https://openalex.org/W7120088840","https://openalex.org/W7124180632","https://openalex.org/W7125635685","https://openalex.org/W7127272498","https://openalex.org/W7127592783","https://openalex.org/W7127948103","https://openalex.org/W7128701972","https://openalex.org/W7128775057","https://openalex.org/W7129780791","https://openalex.org/W7130402983","https://openalex.org/W7130605930","https://openalex.org/W7133351461","https://openalex.org/W7139951136","https://openalex.org/W7140189079","https://openalex.org/W7141148890","https://openalex.org/W7154482439","https://openalex.org/W7157671730","https://openalex.org/W7159662544","https://openalex.org/W7160901314","https://openalex.org/W7160937593","https://openalex.org/W7160955782","https://openalex.org/W7161016054","https://openalex.org/W7166829495"],"related_works":["https://openalex.org/W4414490998","https://openalex.org/W4415318414","https://openalex.org/W7162396178","https://openalex.org/W7215122866","https://openalex.org/W7164002160","https://openalex.org/W4417287612","https://openalex.org/W7134860561","https://openalex.org/W7202185450","https://openalex.org/W7204964375","https://openalex.org/W7220679763"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,41],"from":[2],"human":[3,18],"feedback":[4,59],"(RLHF)":[5],"has":[6],"become":[7],"the":[8,34,54,103],"dominant":[9],"paradigm":[10],"for":[11,148],"aligning":[12],"large":[13],"language":[14],"models":[15],"(LLMs)":[16],"with":[17],"preferences.However,":[19],"traditional":[20],"RLHF":[21],"relies":[22],"on":[23],"scalar":[24],"reward":[25,57,139],"signals":[26],"that":[27,71],"lack":[28],"interpretability":[29],"and":[30,61,82,115,118,137],"fail":[31],"to":[32],"capture":[33],"multifaceted":[35],"nature":[36],"of":[37,56,99,131],"response":[38],"quality.Rubricguided":[39],"reinforcement":[40],"addresses":[42],"these":[43],"limitations":[44],"by":[45],"introducing":[46],"structured,":[47],"interpretable":[48],"evaluation":[49,80],"criteria,":[50],"or":[51],"rubrics,":[52,110,114],"as":[53,74,84,121],"backbone":[55],"design,":[58],"generation,":[60],"policy":[62],"optimization.In":[63],"this":[64,92],"survey,":[65],"we":[66,95,126],"introduce":[67],"a":[68,97,128],"Bayesian":[69],"framework":[70],"defines":[72],"constitutions":[73],"prior":[75],"distributions":[76],"P":[77,90],"(R)":[78],"over":[79],"criteria":[81],"rubrics":[83,122],"conditional":[85],"instantiations":[86],"R":[87],"x":[88],"\u223c":[89],"(R|x).Under":[91],"unified":[93],"view,":[94],"present":[96,127],"taxonomy":[98],"rubric-guided":[100],"RL":[101],"along":[102],"priorposterior":[104],"axis,":[105],"covering":[106],"constitutional":[107],"AI,":[108],"instance-specific":[109],"process-level":[111],"supervision,":[112],"self-evolving":[113],"their":[116],"agentic":[117],"multimodal":[119],"extensions.Furthermore,":[120],"are":[123],"natural-language":[124],"artifacts,":[125],"linguistic":[129,138],"analysis":[130],"how":[132],"granularity":[133],"trade-offs,":[134],"semantic":[135],"drift,":[136],"hacking":[140],"impact":[141],"alignment":[142],"reliability,":[143],"identifying":[144],"key":[145],"open":[146],"problems":[147],"future":[149],"research.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-01T00:00:00"}