{"id":"https://openalex.org/W7113897064","doi":"https://doi.org/10.1145/3765612.3767230","title":"Reward Hacking Mitigation using Verifiable Composite Rewards","display_name":"Reward Hacking Mitigation using Verifiable Composite Rewards","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7113897064","doi":"https://doi.org/10.1145/3765612.3767230"},"language":null,"primary_location":{"id":"doi:10.1145/3765612.3767230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3765612.3767230","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mirza Farhan Bin Tarek","orcid":"https://orcid.org/0009-0009-0403-6442"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirza Farhan Bin Tarek","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"raw_orcid":"https://orcid.org/0009-0009-0403-6442","affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rahmatollah Beheshti","orcid":"https://orcid.org/0000-0001-8912-3063"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahmatollah Beheshti","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"raw_orcid":"https://orcid.org/0000-0001-8912-3063","affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76115351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7436000108718872,"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/T10028","display_name":"Topic Modeling","score":0.7436000108718872,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06019999831914902,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.7595999836921692},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7336000204086304},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.6933000087738037},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5943999886512756},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5152999758720398}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.7595999836921692},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7336000204086304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127000093460083},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5694000124931335},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33500000834465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765612.3767230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765612.3767230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3767230","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6055662035942078}],"awards":[{"id":"https://openalex.org/G3198305074","display_name":null,"funder_award_id":"U54GM104941","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G622962621","display_name":null,"funder_award_id":"2443639","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G785190151","display_name":null,"funder_award_id":"P20GM103446","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W4404783491"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"from":[2],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"has":[6],"recently":[7],"shown":[8],"that":[9,88],"large":[10],"language":[11],"models":[12,125],"(LLMs)":[13],"can":[14],"develop":[15],"their":[16],"own":[17],"reasoning":[18,40,63,99],"without":[19,56],"direct":[20],"supervision.":[21],"However,":[22],"applications":[23],"in":[24],"the":[25,39,67,109,122],"medical":[26],"domain,":[27],"specifically":[28],"for":[29,82],"question":[30],"answering,":[31],"are":[32],"susceptible":[33],"to":[34,65,97,108],"significant":[35],"reward":[36,68,77,94,102,118],"hacking":[37,103,119],"during":[38],"phase.":[41],"Our":[42,85],"work":[43],"addresses":[44],"two":[45],"primary":[46],"forms":[47],"of":[48,124],"this":[49],"behavior:":[50],"i)":[51],"providing":[52],"a":[53,75,114],"final":[54],"answer":[55],"preceding":[57],"reasoning,":[58],"and":[59,104,120],"ii)":[60],"employing":[61],"non-standard":[62],"formats":[64],"exploit":[66],"mechanism.":[69],"To":[70],"mitigate":[71],"these,":[72],"we":[73],"introduce":[74],"composite":[76],"function":[78],"with":[79,91,100],"specific":[80],"penalties":[81],"these":[83],"behaviors.":[84],"experiments":[86],"show":[87],"utilizing":[89,126],"RLVR":[90],"our":[92],"proposed":[93],"model":[95],"leads":[96],"better-formatted":[98],"less":[101],"good":[105],"accuracy":[106],"compared":[107],"baselines.":[110],"This":[111],"approach":[112],"marks":[113],"step":[115],"toward":[116],"reducing":[117],"enhancing":[121],"reliability":[123],"RLVR1.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-11T00:00:00"}