{"id":"https://openalex.org/W4416035888","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.20","title":"Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework","display_name":"Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035888","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.20"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.20","pdf_url":"https://aclanthology.org/2025.findings-emnlp.20.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083955516","display_name":"Zhangyue Yin","orcid":"https://orcid.org/0009-0008-0620-8271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangyue Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100572120","display_name":"Yuhong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YuHong Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063868428","display_name":"Zhao Hui","orcid":"https://orcid.org/0000-0002-7512-3166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Zhao","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.3815000057220459,"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/T13629","display_name":"Text Readability and Simplification","score":0.3815000057220459,"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":0.10970000177621841,"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":0.09000000357627869,"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/word","display_name":"Word (group theory)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3995000123977661},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3328000009059906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33230000734329224},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2549999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6126000285148621},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47209998965263367},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2849999964237213},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.20","pdf_url":"https://aclanthology.org/2025.findings-emnlp.20.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.20","pdf_url":"https://aclanthology.org/2025.findings-emnlp.20.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5091463382","display_name":null,"funder_award_id":"62272165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8775507649","display_name":null,"funder_award_id":"92370201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035888.pdf","grobid_xml":"https://content.openalex.org/works/W4416035888.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7,153],"across":[8,81],"various":[9],"domains.Math":[10],"Word":[11],"Problems":[12],"(MWPs)":[13],"serve":[14],"as":[15,151,170],"a":[16,97,124,186,191,205,247,268],"crucial":[17],"benchmark":[18],"for":[19,127,197,238],"evaluating":[20],"LLMs'":[21],"reasoning":[22,110,179],"abilities.While":[23],"most":[24],"research":[25],"primarily":[26],"focuses":[27],"on":[28,46,90,195],"improving":[29],"accuracy,":[30],"it":[31],"often":[32],"neglects":[33],"understanding":[34],"and":[35,48,109,115,188,261],"addressing":[36],"the":[37,57,217,232,235,240,251,263,280,288,292],"underlying":[38],"patterns":[39,62,108,169],"of":[40,60,78,119,224,234,259,270,282,294],"errors.Current":[41],"error":[42,61,68,72,102,107,120,130,142,158,168],"classification":[43,131],"methods":[44],"rely":[45],"static":[47],"predefined":[49],"categories,":[50],"which":[51,144,308],"limit":[52],"their":[53],"ability":[54],"to":[55,148,174,185],"capture":[56],"full":[58],"spectrum":[59],"in":[63,132,177,214],"mathematical":[64,133,178],"reasoning.To":[65],"enable":[66,116],"systematic":[67],"analysis,":[69],"we":[70,94,122,160,286],"collect":[71],"samples":[73,103],"from":[74,146],"15":[75],"different":[76],"LLMs":[77],"varying":[79],"sizes":[80],"four":[82],"distinct":[83],"MWP":[84],"datasets":[85],"using":[86],"multiple":[87],"sampling":[88],"strategies.Based":[89],"this":[91],"extensive":[92],"collection,":[93],"introduce":[95],"MWPES-300K,":[96],"comprehensive":[98],"dataset":[99,138],"containing":[100],"304,865":[101],"that":[104,137,165],"cover":[105],"diverse":[106],"paths.To":[111],"reduce":[112],"human":[113],"bias":[114],"fine-grained":[117],"analysis":[118],"patterns,":[121,143,159],"propose":[123,161],"novel":[125],"framework":[126],"automated":[128],"dynamic":[129],"reasoning.Experimental":[134],"results":[135],"demonstrate":[136],"characteristics":[139],"significantly":[140],"shape":[141],"evolve":[145],"basic":[147],"complex":[149],"manifestations":[150],"model":[152],"increase.With":[154],"deeper":[155],"insights":[156],"into":[157],"Error-Aware":[162],"Prompting":[163],"(EAP)":[164],"incorporates":[166],"common":[167],"explicit":[171],"guidance,":[172],"leading":[173],"significant":[175],"improvements":[176],"performance.Question:":[180],"Heather's":[181],"razors":[182],"come":[183],"4":[184,275],"pack":[187],"cost":[189,281,290,306],"$4.00":[190],"pack.They":[192],"are":[193],"currently":[194],"sale":[196],"buy":[198],"one":[199,201],"get":[200],"free.She":[202],"also":[203],"has":[204],"$2.00":[206],"coupon.How":[207],"much":[208],"will":[209,305],"each":[210,283],"individual":[211,284,303],"razor":[212,304],"cost,":[213],"cents,":[215],"after":[216],"discount":[218],"if":[219],"she":[220,266],"buys":[221,256],"2":[222,257,271,273],"packs":[223,258],"razors?Correct":[225],"Answer:":[226],"25":[227],"cents.":[228,315],"Analysis:1.The":[229],"calculation":[230],"confused":[231],"concept":[233],"quantity":[236,243],"paid":[237],"versus":[239],"actual":[241],"total":[242,269,289],"received.2.":[244],"Discount":[245],"used":[246],"secondary":[248],"value,":[249],"not":[250],"original":[252],"price.Error":[253],"Solution:Step1:":[254],"Heather":[255],"razors,":[260],"with":[262],"buy-one-get-onefree":[264],"deal,":[265],"gets":[267],"*":[272,311],"=":[274,299,313],"packs.":[276],"Step6:":[277],"To":[278],"find":[279],"razor,":[285],"divide":[287],"by":[291],"number":[293],"razors:":[295],"14":[296],"/":[297],"8":[298],"1.75":[300,310],"dollars.Step7:":[301],"Each":[302],"$1.75,":[307],"is":[309],"100":[312],"175":[314],"Clustering":[316],"AlgorithmEmbedding":[317],"Model":[318],"0.056":[319],"0.05":[320],"-0.13":[321],"0.":[322]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}