odoma/Qwen3-VL-8B-LoRA-ref-parsing
Text Generation • Updated • 1
messages listlengths 3 3 | source stringclasses 3
values | split stringclasses 1
value | mode stringclasses 2
values | category stringclasses 27
values | file_id stringclasses 121
values | ref_count int64 1 10 | language stringclasses 9
values |
|---|---|---|---|---|---|---|---|
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | ENV-SCI | ENV-SCI_54 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 45108 | 3 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 46228 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 34008 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | single | PSY | PSY_99 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 39222 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 1528 | 1 | de |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | single | MUL | MUL_79 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | single | NEU | NEU_81 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | group | null | 32415 | 8 | de |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | single | MATH | MATH_70 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 19733 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 26735 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 34008 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 35926 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 53281 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 34869 | 1 | de |
[
{
"content": "You extract reference metadata.",
"role": "system"
},
{
"content": "Find all bibliographic references and structure them as JSON with authors, titles, publication details.\n\n### Input Text:\nE H Schein. Organizational psychology. 1965",
"role": "user"
},
{
"content": "{\"r... | cex | train | single | NUR | NUR_86 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 35357 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 47961 | 5 | de |
[
{
"content": "You extract reference metadata.",
"role": "system"
},
{
"content": "Find all bibliographic references and structure them as JSON with authors, titles, publication details.\n\n### Input Text:\nWittgenstein, Ludwig (2009 [1953]). Philosophical investigations. London: Blackwell.",
"ro... | excite | train | single | null | 34008 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | single | MUL | MUL_79 | 1 | en |
[
{
"content": "You extract reference metadata.",
"role": "system"
},
{
"content": "Find all bibliographic references and structure them as JSON with authors, titles, publication details.\n\n### Input Text:\n\"Wirtschaftskammer Sloweniens (1991, 1992): Informationsmaterial. Ljubljana.\"\nLuescher, Kur... | excite | train | group | null | 48511 | 4 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | group | COM_SCI | COM-SCI_25 | 8 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | group | null | 31474 | 2 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 18189 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 2713 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 53781 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 2713 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 27482 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 118633 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 20291 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | single | ENV-SCI | ENV-SCI_54 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 18189 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | NUR | NUR_86 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 34008 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | single | AGR-BIO-SCI | AGR-BIO-SCI_1 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | group | PHY-AST | PHY-AST_95 | 2 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 20291 | 1 | en |
[
{
"content": "You extract reference metadata.",
"role": "system"
},
{
"content": "Find all bibliographic references and structure them as JSON with authors, titles, publication details.\n\n### Input Text:\nRaphael, Lutz (2001), »Radikales Ordnungsdenken und die Organisation totalitärer Herrschaft. W... | excite | train | single | null | 118633 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 11413 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | group | null | 4004 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 32415 | 1 | de |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: Wang, Zhengxu (2006): Explaining Regime Strength in China, in: China. An International Journal 4, 2, (Sep.), S. 217-237.",
"role": "user"
},
{
"content": "{\"references\": [{\"reference\": ... | excite | train | single | null | 27667 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | group | ENV-SCI | ENV-SCI_54 | 5 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 118633 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | single | CHE-ENG | CHE-ENG_18 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | group | COM_SCI | COM-SCI_25 | 2 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 35357 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | group | null | 35357 | 6 | de |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 34912 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 30799 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 53281 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | group | null | 32567 | 4 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 36820 | 5 | de |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: 1910 Gobbi U., Un disegno di legge per le imprese d ’ assicurazione sulla vita, Milano.",
"role": "user"
},
{
"content": "{\"references\": [{\"reference\": {\"authors\": [{\"first_name\": \... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | NUR | NUR_86 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | ENE | ENE_45 | 1 | en |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: M Nussbaum. Upheavals of thought. 2001",
"role": "user"
},
{
"content": "{\"references\": [{\"reference\": {\"authors\": [{\"first_name\": \"M\", \"middle_name\": \"\", \"surname\": \"Nussb... | cex | train | group | VET | z_notes_test_3 | 1 | en |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: Deutscher Bundestag (2001): Elfter Bericht zur Entwicklungspolitik der Bundesregierung Drucksache 14/6496.\n\"Schönbach, Klaus (1995): Der Beitrag der Medien zu Europa. Rezeption und Wirkung, in: Erbri... | excite | train | group | null | 35357 | 2 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 31924 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | EN |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | group | null | 9937 | 7 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 5675 | 9 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 48150 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 46228 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 38465 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 35357 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | EAR-PLA-SCI | EAR-PLA-SCI_37 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | ES |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 37955 | 8 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 45544 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | single | null | 39222 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 19733 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | group | DEN | DEN_36 | 5 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 39222 | 9 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | group | SOC-SCI | SOC-SCI_102 | 9 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 34522 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 118633 | 1 | de |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | group | NEU | NEU_81 | 4 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 37955 | 9 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | group | MED | MED_76 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | single | ENV-SCI | ENV-SCI_54 | 1 | en |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | cex | train | group | SOC-SCI | SOC-SCI_102 | 4 | en |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: Markus K Brunnermeier, Jonathan A Parker. Optimal Expectations. American Economic Review. 2005. Vol. 95",
"role": "user"
},
{
"content": "{\"references\": [{\"reference\": {\"authors\": [{\... | cex | train | single | ECO-ECO-FIN | ECO-ECO-FIN_41 | 1 | en |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | excite | train | single | null | 39222 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | cex | train | group | NEU | NEU_81 | 2 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 29413 | 7 | de |
[
{
"content": "You parse reference lists into structured data.",
"role": "system"
},
{
"content": "Task: Identify all complete references below and return JSON.\nExpected output structure:\n- references: array of reference objects\n- Each reference contains: authors (with name parts), full_title, jou... | excite | train | single | null | 34869 | 1 | de |
[
{
"content": "Extract bibliographic references into JSON. Output valid JSON only.",
"role": "system"
},
{
"content": "Convert these references to JSON with fields: authors (first_name, middle_name, surname), full_title, journal_title, volume, issue, pages, publication_date, publisher.\n\n### Input T... | cex | train | single | BIO-GEN-MOL | BIO-GEN-MOL_11 | 1 | en |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | linkedbook | train | single | null | null | 1 | IT |
[
{
"content": "You are a bibliographic reference parser.",
"role": "system"
},
{
"content": "Input: In: Flick, U./Kardorff, E. v./Steinke, I. (Hg.): Qualitative Forschung. Reinbek: Rowohlt, 456-467",
"role": "user"
},
{
"content": "{\"references\": [{\"reference\": {\"authors\": [], \"ful... | excite | train | single | null | 5675 | 1 | de |
[
{
"content": "You are a bibliographic reference parser. Extract full reference entries and output structured JSON. Use empty values for missing fields.",
"role": "system"
},
{
"content": "Parse all references from the text below into JSON format:\n\n{\n\"references\": [\n {\n \"reference\": {\n ... | excite | train | group | null | 46228 | 4 | en |
A fine-tuning dataset for bibliographic reference extraction and parsing, combining LinkedBooks, CEX, and EXCITE datasets into conversation-style examples for LLM SFT.
This dataset teaches models to extract and parse bibliographic references from text into structured JSON format. Examples follow a conversational format with system/user/assistant messages, using various prompt variants for diversity.
Data Sources:
| Field | Type | Description |
|---|---|---|
messages |
list | Conversation messages with role (system/user/assistant) and content |
source |
string | Data source: linkedbook, cex, or excite |
split |
string | Dataset split: train or valid |
mode |
string | Example type: single (1 reference) or group (multiple references) |
language |
string | Language code (e.g., en, de, fr) |
ref_count |
int | Number of references in the example |
file_id |
string|null | Source document ID (for CEX/EXCITE) |
category |
string|null | Document category (for CEX) |
| Split | Examples | Description |
|---|---|---|
train |
~1,708 | Main training data |
valid |
~115 | Validation set |
Distribution:
The dataset is being developed by Yurui Zhu (Odoma). This work is carried out in the context of the EU-funded GRAPHIA project (grant ID: 101188018).