{"id":"https://openalex.org/W6967048876","doi":"https://doi.org/10.48550/arxiv.2407.16931","title":"ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering","display_name":"ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering","publication_year":2024,"publication_date":"2024-07-24","ids":{"openalex":"https://openalex.org/W6967048876","doi":"https://doi.org/10.48550/arxiv.2407.16931"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.16931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16931","pdf_url":"https://arxiv.org/pdf/2407.16931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.16931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen, Xiuying","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiuying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Tairan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tairan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091542874","display_name":"Taicheng Guo","orcid":"https://orcid.org/0000-0001-7919-6912","observed_orcids":["https://orcid.org/0000-0001-7919-6912"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Taicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guo, Kehan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Kehan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Juexiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Juexiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Haoyang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030077358","display_name":"Mingchen Zhuge","orcid":"https://orcid.org/0000-0003-2561-7712","observed_orcids":["https://orcid.org/0000-0003-2561-7712"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuge, Mingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Schmidhuber, J\u00fcrgen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmidhuber, J\u00fcrgen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gao, Xin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665","observed_orcids":["https://orcid.org/0000-0002-3574-5665"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangliang","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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7782999873161316,"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":0.7782999873161316,"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":0.09380000084638596,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.7570000290870667},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.8379999995231628},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.628000020980835},{"id":"https://openalex.org/keywords/chemistry-education","display_name":"chemistry education","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78329998254776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7444999814033508},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47839999198913574},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2407.16931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16931","pdf_url":"https://arxiv.org/pdf/2407.16931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.16931","doi":"https://doi.org/10.48550/arxiv.2407.16931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.16931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.16931","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16931","pdf_url":"https://arxiv.org/pdf/2407.16931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8824524283409119,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1381064067","display_name":null,"funder_award_id":"FCC/1/1976- 45-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"},{"id":"https://openalex.org/G385720824","display_name":null,"funder_award_id":"FCC/1/1976\u201044\u201001","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"},{"id":"https://openalex.org/G5289953175","display_name":null,"funder_award_id":"REI/1/5234-01-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"},{"id":"https://openalex.org/G6969386925","display_name":null,"funder_award_id":"RGC/3/4816\u201001\u201001","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6967048876.pdf","grobid_xml":"https://content.openalex.org/works/W6967048876.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406073177","https://openalex.org/W3128121521","https://openalex.org/W4416098695","https://openalex.org/W4391800539","https://openalex.org/W4392688439","https://openalex.org/W7161125972","https://openalex.org/W4403213735","https://openalex.org/W7117665737","https://openalex.org/W4416245566","https://openalex.org/W4410521503"],"abstract_inverted_index":{"Question":[0],"Answering":[1],"(QA)":[2],"effectively":[3,40,95],"evaluates":[4],"language":[5],"models'":[6],"reasoning":[7],"and":[8,21,37,74,159,209,230,234],"knowledge":[9],"depth.":[10],"While":[11],"QA":[12,29,57],"datasets":[13],"are":[14,130],"plentiful":[15],"in":[16,34],"areas":[17],"like":[18],"general":[19],"domain":[20],"biomedicine,":[22],"academic":[23],"chemistry":[24],"is":[25],"less":[26],"explored.":[27],"Chemical":[28],"plays":[30],"a":[31,55,75,89,150,156,179,193],"crucial":[32],"role":[33],"both":[35],"education":[36],"research":[38,237],"by":[39,99,114,133],"translating":[41],"complex":[42],"chemical":[43,61,97,239],"information":[44],"into":[45],"readily":[46],"understandable":[47],"format.":[48],"Addressing":[49],"this":[50],"gap,":[51],"we":[52,87,139,177],"introduce":[53,88],"ScholarChemQA,":[54],"large-scale":[56],"dataset":[58,64,219],"constructed":[59],"from":[60],"papers.":[62],"This":[63],"reflects":[65],"typical":[66],"real-world":[67],"challenges,":[68],"including":[69],"an":[70],"imbalanced":[71,111],"data":[72,80,143],"distribution":[73,113],"substantial":[76],"amount":[77],"of":[78,110,124,152,174,189],"unlabeled":[79,142],"that":[81,200],"can":[82,232],"be":[83],"potentially":[84],"useful.":[85],"Correspondingly,":[86],"QAMatch":[90,202],"model,":[91],"specifically":[92],"designed":[93],"to":[94,144],"answer":[96],"questions":[98],"fully":[100],"leveraging":[101],"our":[102,201,217,228],"collected":[103],"data.":[104],"We":[105,226],"first":[106],"address":[107],"the":[108,116,121,141,146,165,172,175,186,205],"issue":[109],"label":[112],"re-weighting":[115],"instance-wise":[117],"loss":[118],"based":[119,154],"on":[120,155,216,222,238],"inverse":[122],"frequency":[123],"each":[125],"class,":[126],"ensuring":[127,160],"minority":[128],"classes":[129],"not":[131,214],"dominated":[132],"majority":[134],"ones":[135],"during":[136],"optimization.":[137],"Next,":[138],"utilize":[140],"enrich":[145],"learning":[147],"process,":[148],"generating":[149],"variety":[151],"augmentations":[153],"SoftMix":[157],"operation":[158],"their":[161],"predictions":[162],"align":[163],"with":[164,192],"same":[166],"target,":[167],"i.e.,":[168],"pseudo-labels.":[169],"To":[170],"ensure":[171],"quality":[173],"pseudo-labels,":[176],"propose":[178],"calibration":[180],"procedure":[181],"aimed":[182],"at":[183],"closely":[184],"aligning":[185],"pseudo-label":[187],"estimates":[188],"individual":[190],"samples":[191],"desired":[194],"ground":[195],"truth":[196],"distribution.":[197],"Experiments":[198],"show":[199],"significantly":[203],"outperforms":[204],"recent":[206],"similar-scale":[207],"baselines":[208],"Large":[210],"Language":[211],"Models":[212],"(LLMs)":[213],"only":[215],"ScholarChemQA":[218],"but":[220],"also":[221],"four":[223],"benchmark":[224,229],"datasets.":[225],"hope":[227],"model":[231],"facilitate":[233],"promote":[235],"more":[236],"QA.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}