{"id":"https://openalex.org/W7128680555","doi":"https://doi.org/10.48448/fr78-sh73","title":"DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs","display_name":"DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128680555","doi":"https://doi.org/10.48448/fr78-sh73"},"language":"en","primary_location":{"id":"doi:10.48448/fr78-sh73","doi":"https://doi.org/10.48448/fr78-sh73","is_oa":true,"landing_page_url":"https://doi.org/10.48448/fr78-sh73","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/fr78-sh73","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092998385","display_name":"Oluwanifemi Bamgbose","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bamgbose, Oluwanifemi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125715494","display_name":"Masoud Hashemi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hashemi, Masoud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125739688","display_name":"Jishnu Nair","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nair, Jishnu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016214507","display_name":"Sathwik Tejaswi Madhusudhan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tejaswi Madhusudhan, Sathwik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124099147","display_name":"Aman Tiwari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210167039","display_name":"ServiceNow (United States)","ror":"https://ror.org/05xr0bc04","country_code":"US","type":"company","lineage":["https://openalex.org/I4210167039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiwari, Aman","raw_affiliation_strings":["ServiceNow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ServiceNow","institution_ids":["https://openalex.org/I4210167039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025247775","display_name":"Vikas Yadav","orcid":"https://orcid.org/0000-0003-0378-6216","observed_orcids":["https://orcid.org/0000-0003-0378-6216"]},"institutions":[{"id":"https://openalex.org/I4210167039","display_name":"ServiceNow (United States)","ror":"https://ror.org/05xr0bc04","country_code":"US","type":"company","lineage":["https://openalex.org/I4210167039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yadav, Vikas","raw_affiliation_strings":["ServiceNow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ServiceNow","institution_ids":["https://openalex.org/I4210167039"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8295999765396118,"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":0.8295999765396118,"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":0.1031000018119812,"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":0.021299999207258224,"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/reasoning-llms","display_name":"reasoning LLMs","score":0.8149999976158142},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.41600000858306885},{"id":"https://openalex.org/keywords/test-time-scaling","display_name":"test-time scaling","score":0.6990000009536743},{"id":"https://openalex.org/keywords/hallucination-avoidance","display_name":"hallucination avoidance","score":0.9890000224113464},{"id":"https://openalex.org/keywords/adversarial-prompts","display_name":"adversarial prompts","score":0.781000018119812},{"id":"https://openalex.org/keywords/inference-efficiency","display_name":"inference efficiency","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6225000023841858},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3589000105857849},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.266400009393692},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/fr78-sh73","doi":"https://doi.org/10.48448/fr78-sh73","is_oa":true,"landing_page_url":"https://doi.org/10.48448/fr78-sh73","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/fr78-sh73","doi":"https://doi.org/10.48448/fr78-sh73","is_oa":true,"landing_page_url":"https://doi.org/10.48448/fr78-sh73","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128718468","https://openalex.org/W7129476629","https://openalex.org/W7119493921","https://openalex.org/W4416052617","https://openalex.org/W7155412003","https://openalex.org/W7169114097","https://openalex.org/W4416047842","https://openalex.org/W4415158403","https://openalex.org/W4417097899","https://openalex.org/W7213675684"],"abstract_inverted_index":{"Test-time":[0],"scaling":[1],"has":[2],"significantly":[3],"improved":[4],"large":[5],"language":[6],"model":[7],"(LLM)":[8],"performance,":[9],"enabling":[10],"deeper":[11],"reasoning":[12,20,52,108],"to":[13,24,43,47,71,133],"solve":[14],"complex":[15],"problems.":[16],"However,":[17],"this":[18],"increased":[19],"capability":[21],"also":[22],"leads":[23],"excessive":[25],"token":[26],"generation":[27],"and":[28,54,73,102,116,161],"unnecessary":[29,56],"problem-solving":[30],"attempts.":[31],"We":[32,106],"introduce":[33],"``Don't":[34],"Reason":[35],"Bench":[36,59,87],"(DNR":[37],"Bench)'',":[38],"a":[39,120],"new":[40],"benchmark":[41],"designed":[42,64],"evaluate":[44,107],"LLMs\u2019":[45],"ability":[46],"robustly":[48],"understand":[49,72],"the":[50,82,155],"tricky":[51],"triggers":[53],"avoiding":[55],"generation.":[57],"DNR":[58,86],"consists":[60],"of":[61,81],"150":[62],"adversarially":[63],"prompts":[65],"that":[66,129,143],"are":[67],"easy":[68],"for":[69,79,157],"humans":[70],"respond":[74],"to,":[75],"but":[76],"surprisingly":[77],"not":[78],"many":[80],"recent":[83],"prominent":[84],"LLMs.":[85],"tests":[88],"models'":[89],"abilities":[90],"across":[91],"different":[92],"capabilities,":[93],"such":[94],"as":[95],"instruction":[96],"adherence,":[97],"hallucination":[98],"avoidance,":[99],"redundancy":[100],"filtering,":[101],"unanswerable":[103],"question":[104],"recognition.":[105],"LLMs":[109],"(RLMs),":[110],"including":[111],"DeepSeek-R1,":[112],"OpenAI":[113],"O3-mini,":[114],"Claude-3.7-sonnet":[115],"compare":[117],"them":[118],"against":[119],"powerful":[121],"non-reasoning":[122,145],"model,":[123],"e.g.,":[124],"GPT-4o.":[125],"Our":[126,152],"experiments":[127],"reveal":[128],"RLMs":[130],"generate":[131],"up":[132],"70$\\times$":[134],"more":[135,158],"tokens":[136],"than":[137],"necessary,":[138],"often":[139],"failing":[140],"at":[141],"tasks":[142],"simpler":[144],"models":[146],"handle":[147],"efficiently":[148],"with":[149],"higher":[150],"accuracy.":[151],"findings":[153],"underscore":[154],"need":[156],"effective":[159],"training":[160],"inference":[162],"strategies":[163],"in":[164],"RLMs.":[165]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}