{"id":"https://openalex.org/W7140078914","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.164","title":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","display_name":"Imbalanced Gradients in RL Post-Training of Multi-Task LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140078914","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.164"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.164","pdf_url":"https://aclanthology.org/2026.findings-eacl.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.164.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130371072","display_name":"Runzhe Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runzhe Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130392793","display_name":"Ankur Samanta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Samanta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130331150","display_name":"Ayush Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayush Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130332572","display_name":"Scott Fujimoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Fujimoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000527109","display_name":"Jeongyeol Kwon","orcid":"https://orcid.org/0000-0002-7910-7817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongyeol Kwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130361107","display_name":"Ben Kretzu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Kretzu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130345921","display_name":"Youliang Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youliang Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072012496","display_name":"Kaveh Hassani","orcid":"https://orcid.org/0000-0001-9162-9442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaveh Hassani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113499012","display_name":"Boris Vidolov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Vidolov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090891199","display_name":"Yonathan Efroni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonathan Efroni","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22346643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3137","last_page":"3150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.05999999865889549,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.05999999865889549,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05860000103712082,"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":0.057500001043081284,"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/ectotherm","display_name":"Ectotherm","score":0.3871000111103058},{"id":"https://openalex.org/keywords/climate-change","display_name":"Climate change","score":0.22169999778270721}],"concepts":[{"id":"https://openalex.org/C13376991","wikidata":"https://www.wikidata.org/wiki/Q587698","display_name":"Ectotherm","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3073999881744385},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2912999987602234},{"id":"https://openalex.org/C175605778","wikidata":"https://www.wikidata.org/wiki/Q3299701","display_name":"Natural resource economics","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.2687000036239624},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25450000166893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24779999256134033},{"id":"https://openalex.org/C132651083","wikidata":"https://www.wikidata.org/wiki/Q7942","display_name":"Climate change","level":2,"score":0.22169999778270721},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2206999957561493}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.164","pdf_url":"https://aclanthology.org/2026.findings-eacl.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.164","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.164","pdf_url":"https://aclanthology.org/2026.findings-eacl.164.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140078914.pdf","grobid_xml":"https://content.openalex.org/works/W7140078914.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Runzhe":[0],"Wu,":[1],"Ankur":[2],"Samanta,":[3],"Ayush":[4],"Jain,":[5],"Scott":[6],"Fujimoto,":[7],"Jeongyeol":[8],"Kwon,":[9],"Ben":[10],"Kretzu,":[11],"Youliang":[12],"Yu,":[13],"Kaveh":[14],"Hassani,":[15],"Boris":[16],"Vidolov,":[17],"Yonathan":[18],"Efroni.":[19],"Findings":[20],"of":[21],"the":[22],"Association":[23],"for":[24],"Computational":[25],"Linguistics:":[26],"EACL":[27],"2026.":[28,29]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}
