Eleni Straitouri

I am a PhD student at the Max Planck Institute for Software Systems under the supervision of Dr. Manuel Gomez-Rodriguez. My interests lie broadly in the field of Human-Centered Machine Learning. Presently, my main research focus is on machine assisted decision-making, and more particularly on leveraging AI models to develop robust and trustworthy decision support systems with distribution-free guarantees. Recently, I have also become interested in the evaluation of Large Language Models. In 2024, I received the Google PhD Fellowship in Machine Intelligence for my research on reliably improving decisions of human experts. In 2020, I got my MEng degree in Electrical and Computer Engineering from the National Technical University of Athens.

Publications


Conferences

Counterfactual Token Generation in Large Language Models
4th Conference on Causal Learning and Reasoning (CLeaR), Lausanne, May 2025.
Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri, Stratis Tsirtsis,
Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Prediction-Powered Ranking of Large Language Models
38th Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, December 2024.
Ivi Chatzi, Eleni Straitouri, Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Towards Human-AI Complementarity with Predictions Sets
38th Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, December 2024.
Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri,
Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
38th Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, December 2024.
Eleni Straitouri, Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Designing Decision Support Systems Using Counterfactual Prediction Sets
41st International Conference on Machine Learning (ICML), Vienna, July 2024.
Eleni Straitouri, Manuel Gomez-Rodriguez Spotlight (top 3.5%)
[arxiv] [pdf] [code]
Improving Experts Predictions with Conformal Prediction
40th International Conference on Machine Learning (ICML), Honolulu, July 2023.
Eleni Straitouri, Lequn Wang, Nastaran Okati, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]

Workshops

Evaluation of Large Language Models via Coupled Token Generation
Workshop on Building Trust in LLMs and LLM Applications (ICLR), Singapore,
April 2025.
Nina Corvelo Benz, Stratis Tsirtsis, Eleni Straitouri, Ivi Chatzi, Ander Artola Velasco,
Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Counterfactual Token Generation in Large Language Models
Workshop on Causality and Large Models (NeurIPS), Vancouver, December 2024.
Ivi Chatzi, Nina Corvelo Benz, Eleni Straitouri, Stratis Tsirtsis,
Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
Workshop on Humans, Algorithmic Decision-Making and Society (ICML), Vienna, July 2024.
Eleni Straitouri, Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Prediction-Powered Ranking of Large Language Models
Workshop on Human-centered Evaluation and Auditing of Language Models (CHI), Honolulu, May 2024.
Ivi Chatzi, Eleni Straitouri, Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Designing Decision Support Systems Using Counterfactual Prediction Sets
Workshop on AI and HCI (ICML), Honolulu, July 2023. Best Paper Award
Eleni Straitouri, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Improving Experts Predictions with Conformal Prediction
Workshop on Distribution-Free Uncertainty Quantification (ICML),
Baltimore, July 2022.
Eleni Straitouri, Lequn Wang, Nastaran Okati, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]
Reinforcement Learning Under Algorithmic Triage
Cooperative AI Workshop (NeurIPS), Virtual, December 2021.
Eleni Straitouri, Adish Singla, Vahid Balazadeh Meresht, Manuel Gomez-Rodriguez
[arxiv] [pdf]


Pre-prints

Evaluation of Large Language Models via Coupled Token Generation
Nina Corvelo Benz, Stratis Tsirtsis, Eleni Straitouri, Ivi Chatzi, Ander Artola Velasco,
Suhas Thejaswi, Manuel Gomez-Rodriguez
[arxiv] [pdf] [code]