{"id":"https://openalex.org/W4416035132","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1779","title":"Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems","display_name":"Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035132","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1779"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1779","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1779","pdf_url":"https://aclanthology.org/2025.emnlp-main.1779.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1779.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308763","display_name":"Adam Zahradn\u00edk","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adam Zahradn\u00edk","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113490837","display_name":"Marek \u0160uppa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marek Suppa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120308763"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33215876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35094","last_page":"35109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13280","display_name":"Biomedical and Engineering Education","score":0.028699999675154686,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13280","display_name":"Biomedical and Engineering Education","score":0.028699999675154686,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.02160000056028366,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13844","display_name":"Higher Education Learning Practices","score":0.019600000232458115,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.4383000135421753},{"id":"https://openalex.org/keywords/slovak","display_name":"Slovak","score":0.3659000098705292},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.31450000405311584},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2996000051498413}],"concepts":[{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.41600000858306885},{"id":"https://openalex.org/C2780102689","wikidata":"https://www.wikidata.org/wiki/Q9058","display_name":"Slovak","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3416999876499176},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.296999990940094},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2759000062942505},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C40700","wikidata":"https://www.wikidata.org/wiki/Q1411783","display_name":"Industrial organization","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1779","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1779","pdf_url":"https://aclanthology.org/2025.emnlp-main.1779.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1779","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1779","pdf_url":"https://aclanthology.org/2025.emnlp-main.1779.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8139692357","display_name":null,"funder_award_id":"APVV-21-","funder_id":"https://openalex.org/F4320323251","funder_display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja"}],"funders":[{"id":"https://openalex.org/F4320323251","display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","ror":"https://ror.org/037nx0e70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035132.pdf","grobid_xml":"https://content.openalex.org/works/W4416035132.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,89],"models":[2,71],"show":[3,81],"promising":[4],"performance":[5,78],"on":[6,84,93],"reasoning":[7,77,115],"tasks,":[8],"yet":[9],"evaluation":[10,127],"methods":[11],"for":[12,18,131],"low-resource":[13,117],"languages":[14],"remain":[15],"limited,":[16],"particularly":[17],"complex":[19],"STEM":[20,132],"problemsolving.We":[21],"introduce":[22],"Trojsten":[23],"Benchmark,":[24],"a":[25,42],"Slovak-language":[26],"dataset":[27],"of":[28,96],"1,108":[29],"high-school":[30],"competition":[31],"problems":[32],"with":[33],"reference":[34],"solutions":[35],"across":[36],"mathematics,":[37],"physics,":[38],"and":[39,41,51,69,87,122,128],"programming,":[40],"rubric-based":[43],"LLM":[44],"grading":[45],"framework.Using":[46],"GPT-4":[47],"to":[48,124],"generate":[49],"rubrics":[50],"grade":[52],"solutions,":[53],"we":[54],"observe":[55],"1.05":[56],"average":[57],"absolute":[58],"deviation":[59],"from":[60],"human":[61],"graders":[62],"(5-point":[63],"scale),":[64],"while":[65],"benchmarking":[66],"GPT-3.5-Turbo,GPT-4,":[67],"GPT-4o,":[68],"open-weight":[70],"(Llama":[72],"3,":[73],"Phi-3).We":[74],"quantify":[75],"multistep":[76],"by":[79,111],"difficulty,":[80],"consistent":[82],"underperformance":[83],"harder":[85],"items,":[86],"demonstrate":[88],"sensitivity:":[90],"accuracy":[91],"drops":[92],"English":[94],"translations":[95],"Slovak":[97],"statements,":[98],"evidencing":[99],"challenges":[100],"beyond":[101],"translation.Trojsten":[102],"Benchmark":[103],"complements":[104],"English-centric":[105],"math":[106],"datasets":[107],"(e.g.,":[108],"MATH,":[109],"GSM8K)":[110],"targeting":[112],"open-response,":[113],"rubric-gradable":[114],"under":[116],"linguistic":[118],"framing.We":[119],"release":[120],"code":[121],"data":[123],"enable":[125],"reproducible":[126],"humanaligned":[129],"auto-grading":[130],"in":[133],"under-served":[134],"languages.":[135]},"counts_by_year":[],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-11-08T00:00:00"}
