{"id":"https://openalex.org/W4416037160","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.142","title":"LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators","display_name":"LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037160","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.142"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-industry.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.142","pdf_url":"https://aclanthology.org/2025.emnlp-industry.142.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: Industry Track","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-industry.142.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062872821","display_name":"Mateusz Lango","orcid":"https://orcid.org/0000-0003-2881-5642"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Mateusz Lango","raw_affiliation_strings":["Charles University , Faculty of Mathematics and Physics , Prague , Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University , Faculty of Mathematics and Physics , Prague , Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004829991","display_name":"Ond\u0159ej Du\u0161ek","orcid":"https://orcid.org/0000-0002-1415-1702"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Dusek","raw_affiliation_strings":["Charles University , Faculty of Mathematics and Physics , Prague , Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University , Faculty of Mathematics and Physics , Prague , Czechia","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28986184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2025","last_page":"2040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7170000076293945,"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":0.7170000076293945,"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":0.09600000083446503,"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":0.05220000073313713,"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/python","display_name":"Python (programming language)","score":0.617900013923645},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5626999735832214},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.4740000069141388},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4004000127315521},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.3603000044822693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8136000037193298},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.617900013923645},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5626999735832214},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5296000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170999765396118},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3027999997138977},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-industry.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.142","pdf_url":"https://aclanthology.org/2025.emnlp-industry.142.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: Industry Track","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.18360","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.18360","pdf_url":"https://arxiv.org/pdf/2512.18360","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-industry.142","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.142","pdf_url":"https://aclanthology.org/2025.emnlp-industry.142.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: Industry Track","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037160.pdf","grobid_xml":"https://content.openalex.org/works/W4416037160.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,33,67],"novel":[3],"neurosymbolic":[4],"framework":[5],"for":[6,32,35],"RDF-to-text":[7],"generation,":[8],"in":[9],"which":[10],"the":[11,36,72],"model":[12],"is":[13,52],"\"trained\"":[14],"through":[15],"collaborative":[16],"interactions":[17],"among":[18],"multiple":[19],"LLM":[20,26],"agents":[21,27],"rather":[22],"than":[23],"traditional":[24],"backpropagation.The":[25],"produce":[28],"rule-based":[29],"Python":[30],"code":[31],"generator":[34],"given":[37],"domain,":[38],"based":[39],"on":[40,71],"RDF":[41],"triples":[42],"only,":[43],"with":[44,86],"no":[45,56],"in-domain":[46],"human":[47],"reference":[48],"texts.The":[49],"resulting":[50],"system":[51],"fully":[53],"interpretable,":[54],"requires":[55],"supervised":[57],"training":[58],"data,":[59],"and":[60,74],"generates":[61],"text":[62],"nearly":[63],"instantaneously":[64],"using":[65],"only":[66,87],"single":[68],"CPU.Our":[69],"experiments":[70],"WebNLG":[73],"Open-DialKG":[75],"data":[76],"show":[77],"that":[78],"outputs":[79],"produced":[80],"by":[81],"our":[82],"approach":[83],"reduce":[84],"hallucination,":[85],"slight":[88],"fluency":[89],"penalties":[90],"compared":[91],"to":[92],"finetuned":[93],"or":[94],"prompted":[95],"language":[96],"models.":[97]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-08T00:00:00"}