{"id":"https://openalex.org/W4387848943","doi":"https://doi.org/10.1145/3583780.3615273","title":"Leveraging Knowledge and Reinforcement Learning for Enhanced Reliability of Language Models","display_name":"Leveraging Knowledge and Reinforcement Learning for Enhanced Reliability of Language Models","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387848943","doi":"https://doi.org/10.1145/3583780.3615273"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102714548","display_name":"Nancy Tyagi","orcid":"https://orcid.org/0009-0006-9813-9351"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy Tyagi","raw_affiliation_strings":["University of Maryland, Baltimore County, MD, USA"],"raw_orcid":"https://orcid.org/0009-0006-9813-9351","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007399991","display_name":"Surjodeep Sarkar","orcid":"https://orcid.org/0000-0002-0147-2777"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surjodeep Sarkar","raw_affiliation_strings":["University of Maryland, Baltimore County, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-0147-2777","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023667301","display_name":"Manas Gaur","orcid":"https://orcid.org/0000-0002-5411-2230"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manas Gaur","raw_affiliation_strings":["University of Maryland, Baltimore County, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5411-2230","affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.4839,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71433576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4320","last_page":"4324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8323245048522949},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7119619846343994},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6956108808517456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724412798881531},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.543660044670105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5280671119689941},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47371166944503784},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.41696494817733765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323245048522949},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7119619846343994},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6956108808517456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724412798881531},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.543660044670105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5280671119689941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47371166944503784},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.41696494817733765},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615273","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W2963895422","https://openalex.org/W2978670439","https://openalex.org/W3105935311","https://openalex.org/W3171291687"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"The":[0],"Natural":[1],"Language":[2,18,26],"Processing":[3],"(NLP)":[4],"community":[5],"has":[6,51],"been":[7,53],"using":[8,38],"crowd-sourcing":[9],"techniques":[10],"to":[11,70,87,90],"create":[12],"benchmark":[13],"datasets":[14],"such":[15,29],"as":[16,30,77],"General":[17],"Understanding":[19],"and":[20,75,109],"Evaluation":[21],"(GLUE)":[22],"for":[23,92],"training":[24],"modern":[25],"Models":[27],"(LMs)":[28],"BERT.":[31],"GLUE":[32,100],"tasks":[33],"measure":[34],"the":[35,46,96],"reliability":[36,47,108],"scores":[37],"inter-annotator":[39],"metrics":[40],"-":[41],"Cohen's":[42],"Kappa":[43],"(K).":[44],"However,":[45],"aspect":[48],"of":[49],"LMs":[50],"often":[52],"overlooked.":[54],"To":[55],"counter":[56],"this":[57],"problem,":[58],"we":[59],"explore":[60],"a":[61],"knowledge-guided":[62],"LM":[63],"ensembling":[64,106],"approach":[65,82],"that":[66,105],"leverages":[67],"reinforcement":[68],"learning":[69],"integrate":[71],"knowledge":[72,78,89],"from":[73],"ConceptNet":[74],"Wikipedia":[76],"graph":[79],"embeddings.":[80],"This":[81],"mimics":[83],"human":[84],"annotators":[85],"resorting":[86],"external":[88],"compensate":[91],"information":[93],"deficits":[94],"in":[95],"datasets.":[97],"Across":[98],"nine":[99],"datasets,":[101],"our":[102],"research":[103],"shows":[104],"strengthens":[107],"accuracy":[110],"scores,":[111],"outperforming":[112],"state-of-the-art.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}