Haritz Puerto
PhD Candidate @ UKP Lab, TU Darmstadt
haritz.puerto [AT] tu-darmstadt.de
About
I am a Ph.D. candidate in Machine Learning & Natural Language Processing at UKP Lab in TU Darmstadt, supervised by Prof. Iryna Gurevych. My main research interests are question answering, reasoning, and explainability in large language models. Previously, I worked at the Coleridge Initiative, where I co-organized the Kaggle Competition Show US the Data. I got my master's degree from the School of Computing at KAIST, where I was a research assistant at IR&NLP Lab and was advised by Professor Sung-Hyon Myaeng.
Education
TU DarmstadtJune 2022 - currently
Ph.D. in Computer Science
KAISTSept. 2018 - March 2021
M.S. in Computer Science
University of Malaga Sept. 2012 - July 2017
B.Sc. in Computer Science & Engineering (Summa Cum Laude)
Publications
* indicates equal contribution.Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
Haritz Puerto, Martin Gubri, Sangdoo Yun, Seong Joon Oh
arXiv preprint 2024
Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models
Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych
arXiv preprint 2024
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych
EMNLP 2024
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Ji-Ung Lee, Haritz Puerto, Betty van Aken, Yuki Arase, Jessica Zosa Forde, Leon Derczynski, Andreas Rücklé, Iryna Gurevych, Roy Schwartz, Emma Strubell, Jesse Dodge
arXiv preprint 2023
UKP-SQuARE v3: A Platform for Multi-Agent QA Research
Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva, Haishuo Fang, Hao Zhang, Sewin Tariverdian, Kexin Wang, Iryna Gurevych
ACL 2023 Demo Track
MetaQA: Combining Expert Agents for Multi-Skill Question Answering
Haritz Puerto, Gözde Gül Şahin, Iryna Gurevych
EACL 2023.
Regularization of Distinct Strategies for Unsupervised Question Generation
Junmo Kang*, Giwon Hong*, Haritz Puerto*, Sung-Hyon Myaeng
In Proceedings of Findings of EMNLP, 2020.
Let Me Know What to Ask: Interrogative-Word-Aware Question Generation
Junmo Kang*, Haritz Puerto*, Sung-Hyon Myaeng
In Proceedings of MRQA@EMNLP, 2019.
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
Haritz Puerto, Martin Gubri, Sangdoo Yun, Seong Joon Oh
arXiv preprint 2024
Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models
Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych
arXiv preprint 2024
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
Haritz Puerto, Martin Tutek, Somak Aditya, Xiaodan Zhu, Iryna Gurevych
EMNLP 2024
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Ji-Ung Lee, Haritz Puerto, Betty van Aken, Yuki Arase, Jessica Zosa Forde, Leon Derczynski, Andreas Rücklé, Iryna Gurevych, Roy Schwartz, Emma Strubell, Jesse Dodge
arXiv preprint 2023
UKP-SQuARE: An Interactive Tool for Teaching Question Answering
Haishuo Fang, Haritz Puerto, Iryna Gurevych
BEA Workshop@ACL 2023
UKP-SQuARE v3: A Platform for Multi-Agent QA Research
Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva, Haishuo Fang, Hao Zhang, Sewin Tariverdian, Kexin Wang, Iryna Gurevych
ACL 2023 Demo Track
MetaQA: Combining Expert Agents for Multi-Skill Question Answering
Haritz Puerto, Gözde Gül Şahin, Iryna Gurevych
EACL 2023.
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
Rachneet Sachdeva*, Haritz Puerto*, Tim Baumgärtner, Sewin Tariverdian, Hao Zhang, Kexin Wang, Hossain Shaikh Saadi, Leonardo F. R. Ribeiro, Iryna Gurevych
AACL 2022 Demo Track
UKP-SQUARE: An Online Platform for Question Answering Research
Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Max Eichler, Gregor Geigle, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Şahin, Iryna Gurevych
ACL 2022 Demo Track
Regularization of Distinct Strategies for Unsupervised Question Generation
Junmo Kang*, Giwon Hong*, Haritz Puerto*, Sung-Hyon Myaeng
In Proceedings of Findings of EMNLP, 2020.
Let Me Know What to Ask: Interrogative-Word-Aware Question Generation
Junmo Kang*, Haritz Puerto*, Sung-Hyon Myaeng
In Proceedings of MRQA@EMNLP, 2019.
Analysis of the Semantic Answer Types to Understand the Limitations of MRQA Models
Doyeon Lim*, Haritz Puerto*, Sung-Hyon Myaeng
In Journal of KIISE, 2020.
Analysis of Answer Type Application Ability of State-of-the-Art Reading Comprehension Models for Question Answering Task
Haritz Puerto*, Doyeon Lim*, Sung-Hyon Myaeng
In Proceedings of Korean Computer Congress, 2019. (Best Paper Award)
Teaching
I am always looking for undergraduate/master students interested in doing their thesis on NLP. If you are interested in any of my research topics, please contact me as soon as possible, I try to supervise one student every semester. I also supervise Hiwis (research assistants), but this depends on projects availability.
-
I've been teaching the following courses:
- Guest lecture about QA in the NLP course (Spring Semester 23) @ Koç University (Instructor: Prof. Gözde Gül Şahin).
- Guest lecture about QA in the course NLP4Web (Winter Semester 22/23) @ TU Darmstadt (Instructor: Prof. Iryna Gurevych).
- Data Analysis Software Project for Natural Language (Winter Semester 22/23) @ TU Darmstadt.
- Guest Lecture about QA in the course Deep Learning for NLP (2022)@TU Darmstadt (Instructor: Prof. Ivan Habernal).
-
Supervised BSc/Msc Students:
- Hao Zhang: Groudning Generative LM with Knwoledge Graphs for Commonsense Reasoning
- Sewin Tariverdian: Fusing Structured with Unstructured Modalities for Multi-Hop QA
- Soulaima Khamari: NLI as a Multi-Agent System for QA
Service
-
Reviewer:
- ACL Rolling Review: Nov. 2021, - Today; COLING 2022, EMNLP 2021
-
Invited Talks:
- UKP-SQuARE @ Huawei Search Engine Academic Workshop, November 2022
- ScaDS.AI Machine Learning: QA Research, July 2022
- We Decentralize Tech Podcast: Making AI Answer Questions (in Spanish), February 2022
Vitæ
Full Resume in PDF.
-
NT Parameter Lab Jul. 2024 - Feb. 2025Research Intern
-
UKP Lab@TU Darmstadt Jun. 2021 -Research Assistant
-
Coleridge Initiative Jan. 2021 - May 2021Data Scientist
-
KAIST Sept. 2018 - Mar. 2021M.S. in Computer Science
IR&NLP Lab -
Claroflex Jul. 2015 - Jul. 2017Software Engineer
-
University of Malaga Sep. 2012 - Jul. 2017B.S. in Computer Science & Engineering
Summa Cum Laude