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.

Service

Vitæ

Full Resume in PDF.