---
title: "Generative Information Extraction from — Winkle 2026"
description: "The paper tackles the problem of turning German-language biographical texts, mostly literature encyclopedia entries, into structured records for the…"
authors: ["Robin Winkle", "Manfred Stede", "Jörn Kreutel"]
year: 2026
venue: "Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026"
source: "https://aclanthology.org/2026.latechclfl-1.30/"
doi: "10.18653/v1/2026.latechclfl-1.30"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/winkle-2026-generative-information-extraction-biographical-sources/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/winkle-2026-generative-information-extraction-biographical-sources/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/) / Generative Information Extraction from Biographical Sources

# Generative Information Extraction from Biographical Sources

**Authors:** Robin Winkle, [Manfred Stede](https://md.research.elamur.ai/free/en/authors/manfred-stede/), Jörn Kreutel · **Year:** 2026 · **Venue:** Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026 · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.latechclfl-1.30/) · [PDF](https://aclanthology.org/2026.latechclfl-1.30.pdf) · [DOI 10.18653/v1/2026.latechclfl-1.30](https://doi.org/10.18653/v1/2026.latechclfl-1.30) · [OpenAlex](https://openalex.org/W7140122823)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
The paper tackles the problem of turning German-language biographical texts, mostly literature encyclopedia entries, into structured records for the FLFDDR project. That project is building a bio-bibliographical database of roughly 3,400 authors from the GDR literary field. So far, only about a tenth of these authors have been entered by hand, so semi-automation is needed to scale.

The authors build an end-to-end Generative IE (GenIE) framework that prompts open-source LLMs (Qwen-2.5-32B and Llama-3-70B-Instruct). Each extracted fact is a five-field unit, and every unit keeps a pointer to the text fragment it came from so humans can check it. The team tests several prompt engineering strategies. Because values are generated freely rather than chosen from fixed sets, exact matching is too harsh, so they introduce an evaluation metric based on embedding similarity.

On an unpublished annotated subset, precision stays moderate and fairly stable, while recall varies widely. Simple measures help most: clear instructions and few-shot examples. This is the first systematic study of GenIE for biographical sources in the Digital Humanities.

## Key points
- **Evaluation data:** 188 articles from 72 sources, annotated by five trained student assistants, yielding 6,787 information units. These come from a corpus of about 600 sources, including around 2,300 articles from 150 encyclopedias and handbooks.
- **Output unit format:** SUBJECT, EVENT TYPE, ATTRIBUTE, VALUE and SOURCE FRAGMENT.
  - Event types and attributes come from the FLFDDR data model's predefined lists.
  - Values are unconstrained.
- **Results:**
  - Precision ranged from about 0.61 to 0.71.
  - Recall ranged from about 0.33 to 0.75.
  - F1 ranged from roughly 0.45 to 0.68 across configurations.
  - Recall and F1 correlated strongly with extraction density, so generating too little hurts more than generating somewhat too much.
- **Prompting strategies:** Few-shot prompting and clear formulations gave the most consistent gains. Chain-of-thought (CoT) added little, and the multi-step (sequential) prompting variant reached the lowest recall.
- **Manual error analysis:**
  - Many apparent false positives were actually facts missing from the gold annotations.
  - Outputs showed a bias toward extracting dates.
  - The metric sometimes failed on historical name variants, such as Chemnitz vs. Karl-Marx-Stadt.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) · [History & humanities](https://md.research.elamur.ai/free/en/shelves/history/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{winkle2026generative,
  title = {{Generative Information Extraction from Biographical Sources}},
  author = {Winkle, Robin and Stede, Manfred and Kreutel, Jörn},
  booktitle = {Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026},
  year = {2026},
  doi = {10.18653/v1/2026.latechclfl-1.30},
  url = {https://doi.org/10.18653/v1/2026.latechclfl-1.30}
}
```

- [← previous Generation of Instruction and Preference Dataset for Improving Japanese Instruction Following in LLMs](https://md.research.elamur.ai/free/en/papers/moriyama-2026-generation-instruction-preference-dataset-improving/)
- [next → GENIUS Keylog Corpus - a German High School Student Corpus with Keystroke Logging Data](https://md.research.elamur.ai/free/en/papers/schaller-2026-genius-keylog-corpus-german-high/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/5/)

## References

26 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rishabh Agarwal, Avi Singh, Lei Zhang, Bernd Bohnet, Luis Rosias, Stephanie C. Y. Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D. Co-Reyes, Eric Chu, Feryal M. P. Behbahani, Aleksandra Faust, and Hugo Larochelle. 2024. Many-shot in-context learning. In Advances in Neural Informatio… [find](https://scholar.google.com/scholar?q=Rishabh+Agarwal%2C+Avi+Singh%2C+Lei+Zhang%2C+Bernd+Bohnet%2C+Luis+Rosias%2C+Stephanie+C%2E+Y%2E+Chan%2C+Biao+Zhang%2C+Ankesh+Anand%2C+Zaheer+Abbas%2C+Azade+Nova%2C+John+D%2E+Co%2DReyes%2C+Eric+Chu%2C+Feryal+M%2E+P%2E+Behbahani%2C+Aleksand) [our card](https://md.research.elamur.ai/free/en/papers/agarwal-2024-many-shot-context-learning/)
2. John Dagdelen, Alexander Dunn, Sanghoon Lee, Nicholas Walker, Andrew S. Rosen, Gerbrand Ceder, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra,… [find](https://scholar.google.com/scholar?q=John+Dagdelen%2C+Alexander+Dunn%2C+Sanghoon+Lee%2C+Nicholas+Walker%2C+Andrew+S%2E+Rosen%2C+Gerbrand+Ceder%2C+Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Ma)
3. Akshay Goel, Almog Gueta, Omry Gilon, Chang Liu, Sofia Erell, Lan Huong Nguyen, Xiaohong Hao, Bolous Jaber, Shashir Reddy, Rupesh Kartha, Jean Steiner, Itay Laish, and Amir Feder. 2023. Llms accelerate annotation for medical information extraction. In Machine Learning for Health, ML4H@NeurIPS 2023,… [find](https://scholar.google.com/scholar?q=Akshay+Goel%2C+Almog+Gueta%2C+Omry+Gilon%2C+Chang+Liu%2C+Sofia+Erell%2C+Lan+Huong+Nguyen%2C+Xiaohong+Hao%2C+Bolous+Jaber%2C+Shashir+Reddy%2C+Rupesh+Kartha%2C+Jean+Steiner%2C+Itay+Laish%2C+and+Amir+Feder%2E+2023%2E+Llms+accelerat)
4. Bowen Gu, Vivian Shao, Ziqian Liao, Valentina Carducci, Santiago Romero Brufau, Jie Yang, and Rishi J. Desai. 2025. Scalable information extraction from free text electronic health records using large language models. BMC Medical Research Methodology, 25(1):23. [find](https://scholar.google.com/scholar?q=Bowen+Gu%2C+Vivian+Shao%2C+Ziqian+Liao%2C+Valentina+Carducci%2C+Santiago+Romero+Brufau%2C+Jie+Yang%2C+and+Rishi+J%2E+Desai%2E+2025%2E+Scalable+information+extraction+from+free+text+electronic+health+records+using+large)
5. Yan Hu, Qingyu Chen, Jingcheng Du, Xueqing Peng, Vipina Kuttichi Keloth, Xu Zuo, Yujia Zhou, Zehan Li, Xiaoqian Jiang, Zhiyong Lu, Kirk Roberts, and Hua Xu. 2024. Improving large language models for clinical named entity recognition via prompt engineering. J. Am. Medical Informatics Assoc., 31(9):18… [find](https://scholar.google.com/scholar?q=Yan+Hu%2C+Qingyu+Chen%2C+Jingcheng+Du%2C+Xueqing+Peng%2C+Vipina+Kuttichi+Keloth%2C+Xu+Zuo%2C+Yujia+Zhou%2C+Zehan+Li%2C+Xiaoqian+Jiang%2C+Zhiyong+Lu%2C+Kirk+Roberts%2C+and+Hua+Xu%2E+2024%2E+Improving+large+language+models+for+c)
6. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst., 43(2). [find](https://scholar.google.com/scholar?q=Lei+Huang%2C+Weijiang+Yu%2C+Weitao+Ma%2C+Weihong+Zhong%2C+Zhangyin+Feng%2C+Haotian+Wang%2C+Qianglong+Chen%2C+Weihua+Peng%2C+Xiaocheng+Feng%2C+Bing+Qin%2C+and+Ting+Liu%2E+2025%2E+A+survey+on+hallucination+in+large+language+mo) [our card](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/)
7. We are deeply grateful to the FLFDDR project team for creating the corpus that made this study possible. We would also like to thank the reviewers for their valuable and detailed feedback. [find](https://scholar.google.com/scholar?q=We+are+deeply+grateful+to+the+FLFDDR+project+team+for+creating+the+corpus+that+made+this+study+possible%2E+We+would+also+like+to+thank+the+reviewers+for+their+valuable+and+detailed+feedback%2E)
8. Pierre Bourdieu. 1992. Les règles de l’art: genèse et structure du champ littéraire. Editions du Seuil, Paris. [find](https://scholar.google.com/scholar?q=Pierre+Bourdieu%2E+1992%2E+Les+r%C3%A8gles+de+l%E2%80%99art%3A+gen%C3%A8se+et+structure+du+champ+litt%C3%A9raire%2E+Editions+du+Seuil%2C+Paris%2E)
9. Kristin A. Persson, and Anubhav Jain. 2024. Structured information extraction from scientific text with large language models. Nature Communications, 15(1):1418. [find](https://scholar.google.com/scholar?q=Kristin+A%2E+Persson%2C+and+Anubhav+Jain%2E+2024%2E+Structured+information+extraction+from+scientific+text+with+large+language+models%2E+Nature+Communications%2C+15%281%29%3A1418%2E)
10. Martin Josifoski, Nicola De Cao, Maxime Peyrard, Fabio Petroni, and Robert West. 2022. Genie: Generative information extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022, Seattle, WA,… [find](https://scholar.google.com/scholar?q=Martin+Josifoski%2C+Nicola+De+Cao%2C+Maxime+Peyrard%2C+Fabio+Petroni%2C+and+Robert+West%2E+2022%2E+Genie%3A+Generative+information+extraction%2E+In+Proceedings+of+the+2022+Conference+of+the+North+American+Chapter+of+)
11. Muhammad Ali Khan, Umair Ayub, Syed Arsalan Ahmed Naqvi, Kaneez Zahra Rubab Khakwani, Zaryab bin Riaz Sipra, Ammad Raina, Sihan Zhou, Huan He, Amir Saeidi, Bashar Hasan, Robert Bryan Rumble, Danielle S. Bitterman, Jeremy L. Warner, Jia Zou, Amye J. Tevaarwerk, Konstantinos Leven-takos, Kenneth L. Ke… [find](https://scholar.google.com/scholar?q=Muhammad+Ali+Khan%2C+Umair+Ayub%2C+Syed+Arsalan+Ahmed+Naqvi%2C+Kaneez+Zahra+Rubab+Khakwani%2C+Zaryab+bin+Riaz+Sipra%2C+Ammad+Raina%2C+Sihan+Zhou%2C+Huan+He%2C+Amir+Saeidi%2C+Bashar+Hasan%2C+Robert+Bryan+Rumble%2C+Danielle+)
12. Yaxuan Kong, Yuqi Nie, Xiaowen Dong, John M. Mulvey, H. Vincent Poor, Qingsong Wen, and Stefan Zohren. 2024. Large language models for financial and investment management: Applications and benchmarks. Journal of Portfolio Management, 51(2):162 – 210. Cited by: 2. [find](https://scholar.google.com/scholar?q=Yaxuan+Kong%2C+Yuqi+Nie%2C+Xiaowen+Dong%2C+John+M%2E+Mulvey%2C+H%2E+Vincent+Poor%2C+Qingsong+Wen%2C+and+Stefan+Zohren%2E+2024%2E+Large+language+models+for+financial+and+investment+management%3A+Applications+and+benchmarks%2E)
13. Jörn Kreutel, Thomas Möbius, Birgit Dahlke, and Steffen Martus. 2023. Forschungsplattform Literarisches Feld DDR – Ein Werkstattbericht zur prosopographis-chen Erfassung von Schriftsteller:innen in der DDR. In Helmuth Albrecht, Michael Farrenkopf, Helmut Maier, and Torsten Meyer, editors, Historisch… [find](https://scholar.google.com/scholar?q=J%C3%B6rn+Kreutel%2C+Thomas+M%C3%B6bius%2C+Birgit+Dahlke%2C+and+Steffen+Martus%2E+2023%2E+Forschungsplattform+Literarisches+Feld+DDR+%E2%80%93+Ein+Werkstattbericht+zur+prosopographis%2Dchen+Erfassung+von+Schriftsteller%3Ainnen+in+de)
14. Huaxia Li, Haoyun Gao, Chengzhang Wu, and Miklos A. Vasarhelyi. 2025. Extracting financial data from unstructured sources: Leveraging large language models. Journal of Information Systems, 39(1):135 – 156. Cited by: 5. [find](https://scholar.google.com/scholar?q=Huaxia+Li%2C+Haoyun+Gao%2C+Chengzhang+Wu%2C+and+Miklos+A%2E+Vasarhelyi%2E+2025%2E+Extracting+financial+data+from+unstructured+sources%3A+Leveraging+large+language+models%2E+Journal+of+Information+Systems%2C+39%281%29%3A135+%E2%80%93)
15. Shiye Li and Li Yi. 2024. A few-shot entity relation extraction method in the legal domain based on large language models. In Proceedings of the 2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI ’24, page 580–586, New York,… [find](https://scholar.google.com/scholar?q=Shiye+Li+and+Li+Yi%2E+2024%2E+A+few%2Dshot+entity+relation+extraction+method+in+the+legal+domain+based+on+large+language+models%2E+In+Proceedings+of+the+2024+Guangdong%2DHong+Kong%2DMacao+Greater+Bay+Area+Interna)
16. Yu Liu, Duantengchuan Li, Kaili Wang, Zhuoran Xiong, Fobo Shi, Jian Wang, Bing Li, and Bo Hang. 2024. Are llms good at structured outputs? A benchmark for evaluating structured output capabilities in llms. Inf. Process. Manag., 61(5):103809. [find](https://scholar.google.com/scholar?q=Yu+Liu%2C+Duantengchuan+Li%2C+Kaili+Wang%2C+Zhuoran+Xiong%2C+Fobo+Shi%2C+Jian+Wang%2C+Bing+Li%2C+and+Bo+Hang%2E+2024%2E+Are+llms+good+at+structured+outputs%3F+A+benchmark+for+evaluating+structured+output+capabilities+in+)
17. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with… [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+Shashank+Gupta%2C+Bodhisattwa+Prasad+Majumder%2C+Katherine+Her)
18. Andrew McCallum. 2005. Information extraction: distilling structured data from unstructured text. ACM Queue, 3(9):48–57. [find](https://scholar.google.com/scholar?q=Andrew+McCallum%2E+2005%2E+Information+extraction%3A+distilling+structured+data+from+unstructured+text%2E+ACM+Queue%2C+3%289%29%3A48%E2%80%9357%2E)
19. Alistair Plum, Marcos Zampieri, Constantin Orasan, Eveline Wandl-Vogt, and Ruslan Mitkov. 2019. Large-scale data harvesting for biographical data. In Proceedings of the Third Conference on Biographical Data in a Digital World 2019, Varna, Bulgaria, September 5-6, 2019, volume 3152 of CEUR Workshop P… [find](https://scholar.google.com/scholar?q=Alistair+Plum%2C+Marcos+Zampieri%2C+Constantin+Orasan%2C+Eveline+Wandl%2DVogt%2C+and+Ruslan+Mitkov%2E+2019%2E+Large%2Dscale+data+harvesting+for+biographical+data%2E+In+Proceedings+of+the+Third+Conference+on+Biographica)
20. Maciej P. Polak and Dane Morgan. 2023. Extracting accurate materials data from research papers with conversational language models and prompt engineering - example of chatgpt. CoRR, abs/2303.05352. — [arXiv:2303.05352](https://arxiv.org/abs/2303.05352) [find](https://scholar.google.com/scholar?q=Maciej+P%2E+Polak+and+Dane+Morgan%2E+2023%2E+Extracting+accurate+materials+data+from+research+papers+with+conversational+language+models+and+prompt+engineering+%2D+example+of+chatgpt%2E+CoRR%2C+abs%2F2303%2E05352%2E+%E2%80%94+)
21. Rishabh Ranjan, H. Vathsala, and Shashidhar G. Koolagudi. 2022. Profile generation from web sources: an information extraction system. Soc. Netw. Anal. Min., 12(1):2. [find](https://scholar.google.com/scholar?q=Rishabh+Ranjan%2C+H%2E+Vathsala%2C+and+Shashidhar+G%2E+Koolagudi%2E+2022%2E+Profile+generation+from+web+sources%3A+an+information+extraction+system%2E+Soc%2E+Netw%2E+Anal%2E+Min%2E%2C+12%281%29%3A2%2E)
22. Yongliang Shen, Zeqi Tan, Shuhui Wu, Wenqi Zhang, Rongsheng Zhang, Yadong Xi, Weiming Lu, and Yueting Zhuang. 2023. Promptner: Prompt locating and typing for named entity recognition. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Yongliang+Shen%2C+Zeqi+Tan%2C+Shuhui+Wu%2C+Wenqi+Zhang%2C+Rongsheng+Zhang%2C+Yadong+Xi%2C+Weiming+Lu%2C+and+Yueting+Zhuang%2E+2023%2E+Promptner%3A+Prompt+locating+and+typing+for+named+entity+recognition%2E+In+Proceedings+o)
23. Jouni Tuominen, Eero Hyvönen, and Petri Leskinen. 2017. Bio CRM: A data model for representing biographical data for prosopographical research. In Proceedings of the Second Conference on Biographical Data in a Digital World 2017, Linz, Austria, November 6-7, 2017, volume 2119 of CEUR Workshop Procee… [find](https://scholar.google.com/scholar?q=Jouni+Tuominen%2C+Eero+Hyv%C3%B6nen%2C+and+Petri+Leskinen%2E+2017%2E+Bio+CRM%3A+A+data+model+for+representing+biographical+data+for+prosopographical+research%2E+In+Proceedings+of+the+Second+Conference+on+Biographical+)
24. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi… [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Xuezhi+Wang%2C+Dale+Schuurmans%2C+Maarten+Bosma%2C+Brian+Ichter%2C+Fei+Xia%2C+Ed+H%2E+Chi%2C+Quoc+V%2E+Le%2C+and+Denny+Zhou%2E+2022%2E+Chain%2Dof%2Dthought+prompting+elicits+reasoning+in+large+language+models%2E+In+Ad) [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/)
25. Xiahua Wei, Naveen Kumar, and Han Zhang. 2025. Addressing bias in generative AI: challenges and research opportunities in information management. Inf. Manag., 62(2):104103. [find](https://scholar.google.com/scholar?q=Xiahua+Wei%2C+Naveen+Kumar%2C+and+Han+Zhang%2E+2025%2E+Addressing+bias+in+generative+AI%3A+challenges+and+research+opportunities+in+information+management%2E+Inf%2E+Manag%2E%2C+62%282%29%3A104103%2E)
26. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 43 others. 2024. Qwen2 technical report. CoRR, abs/2407.1067… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)