2 PhDs in NLP: LLM Reasoning for Uncertainty Communication and Explanation in Healthcare

Each of the two PhD positions is expected to carry out the following tasks in support of the corresponding project described above.

Tasks and responsibilities: 

• leading state-of-the art research on the project described;
• collaborating with researchers in the network and beyond;
• publishing academic papers in peer-reviewed international conferences and journals in NLP, ML, and related fields;
• presenting your work in national and international venues;
• assisting in teaching duties, for example as teaching assistant for bachelor and master’s courses, and supervising bachelor and master’s final projects;
• engaging in lab, institute, and research center activities, such as seminars and various rotating organizational roles;
• completing your PhD thesis within the appointment duration of four years.

Each of the two PhD positions is expected to carry out the following tasks in support of the corresponding project described above.

Tasks and responsibilities: 

• leading state-of-the art research on the project described;
• collaborating with researchers in the network and beyond;
• publishing academic papers in peer-reviewed international conferences and journals in NLP, ML, and related fields;
• presenting your work in national and international venues;
• assisting in teaching duties, for example as teaching assistant for bachelor and master’s courses, and supervising bachelor and master’s final projects;
• engaging in lab, institute, and research center activities, such as seminars and various rotating organizational roles;
• completing your PhD thesis within the appointment duration of four years.

A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is 01/03/2027. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 3,204 to € 4,051 (scale P). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile Promovendus  is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Curious about our extensive secondary benefits package? Read more about our benefits 

A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is 01/03/2027. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 3,204 to € 4,051 (scale P). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile Promovendus  is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Curious about our extensive secondary benefits package? Read more about our benefits 

We invite applications for two PhD positions within a new Horizon Europe project ‘Bringing Explainability, Verifiability and Trustworthiness into Multimodal LLMs in the Clinical Practice’. Our team is researching how uncertainty, interpretability and explanations work together to help users judge when to rely on automated decisions. The two successful candidates will join us in advancing the state-of-the-art of techniques for explainability and uncertainty representation in LLM-based reasoning agents, with a particular focus on challenging healthcare data.

The research will explore how to best represent and communicate the state of uncertainty of a generative model, as well as how to best extract, organise and communicate supporting explanations of a model’s response. As healthcare data are composed of long, multimodal, structured and unstructured clinical documents, the project will also involve research into long-context reasoning and tool use.

The two positions will contribute to these shared research themes, with room to develop distinct questions and approaches. We welcome applicants with a broad range of interests, including natural language processing, explainable AI, machine learning, human-computer interaction, and related fields.

Possible directions include, but are not limited to:

PhD 1:

• Structured and explainable representations of uncertainty (e.g., hierarchical Bayesian models, graph-based representations, structure prediction).
• Mathematical tools for uncertainty representation beyond probability (e.g., possibility measures, belief functions, ranking functions).
• Cognitively plausible approaches (e.g., from psychology and psycholinguistics) to uncertainty representation and communication.
• Evaluation of uncertainty quantification usefulness.

PhD 2:

• Conversational and configurable evidence-grounded, uncertainty-aware explanations (e.g., informed by input/data/causal attribution).
• Explanation methods for long and multimodal clinical records, including how to locate, organise, and cite relevant evidence across documents.
• Developing XAI tool-using agents.
• Evaluation of explanation reliability and usefulness (incl., human-centred studies of how explanations support understanding and decision-making)

The successful candidates will work in a team together with Wilker Aziz and Vlad Niculae, and two postdocs, within several larger collaboration networks:

• A Horizon Europe consortium with more than a dozen partner institutes from Europe, UK and Canada
• The Language Technology lab at the Informatics Institute at UvA
• The Natural Language Processing unit at the Institute for, Logic, Language, and Computation at UvA
• Potentially, the ELLIS international doctoral network.

• A master’s degree (completed or very near completion) with a thesis in Natural Language Processing, Machine Learning, Computer Science, or similar relevant areas;
• Curiosity and motivation for pursuing fundamental academic research;
• A good background in natural language processing and machine learning;
• Comfort with scientific programming, training ML models.
• Professional command of the English language;
• A commitment to maintaining an inclusive, collaborative, diverse, and supportive work environment.

The Faculty of Science has a student body of around 8,000, as well as 1,800 members of staff working in education, research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works, be it elementary particles, the birth of the universe or the functioning of the brain.

The mission of the Informatics Institute (IvI) is to perform curiosity-driven and use-inspired fundamental research in Computer Science. The main research themes are Artificial Intelligence, Computational Science and Systems and Network Engineering. Our research involves complex information systems at large, with a focus on collaborative, data driven, computational and intelligent systems, all with a strong interactive component.

The Language Technology Lab (LTL) is a research group focusing on information access from natural language data. Our work ranges from basic research in natural language processing to key applications in human language technology, and covers areas such as machine translation, summarization, question answering, language modeling, and image captioning.

The Institute for Logic, Language and Computation (ILLC) is home to a thriving community of scholars, including philosophers, logicians, mathematicians, computer scientists, linguists, musicologists, and cognitive scientists, who share a fascination with the interdisciplinary study of information. At the ILLC we combine the problem-solving skills from the sciences with the holistic and reflective view of the humanities to discover the principles that regulate information processing and find answers to some of the hardest challenges of our time.

One of the PhD positions is formally embedded in the LTL at IvI, and the other in the NLP unit at ILLC. Both will be co-supervised by Wilker Aziz and Vlad Niculae.

Want to know more about our organisation? Read more about working at the University of Amsterdam.

Are you passionate about uncertainty and explainability of large language models in healthcare? We invite applications for two PhD positions on language model reasoning for uncertainty communication and explanation in healthcare.

We invite applications for two PhD positions within a new Horizon Europe project ‘Bringing Explainability, Verifiability and Trustworthiness into Multimodal LLMs in the Clinical Practice’. Our team is researching how uncertainty, interpretability and explanations work together to help users judge when to rely on automated decisions. The two successful candidates will join us in advancing the state-of-the-art of techniques for explainability and uncertainty representation in LLM-based reasoning agents, with a particular focus on challenging healthcare data.

The research will explore how to best represent and communicate the state of uncertainty of a generative model, as well as how to best extract, organise and communicate supporting explanations of a model’s response. As healthcare data are composed of long, multimodal, structured and unstructured clinical documents, the project will also involve research into long-context reasoning and tool use.

The two positions will contribute to these shared research themes, with room to develop distinct questions and approaches. We welcome applicants with a broad range of interests, including natural language processing, explainable AI, machine learning, human-computer interaction, and related fields.

Possible directions include, but are not limited to:

PhD 1:

• Structured and explainable representations of uncertainty (e.g., hierarchical Bayesian models, graph-based representations, structure prediction).
• Mathematical tools for uncertainty representation beyond probability (e.g., possibility measures, belief functions, ranking functions).
• Cognitively plausible approaches (e.g., from psychology and psycholinguistics) to uncertainty representation and communication.
• Evaluation of uncertainty quantification usefulness.

PhD 2:

• Conversational and configurable evidence-grounded, uncertainty-aware explanations (e.g., informed by input/data/causal attribution).
• Explanation methods for long and multimodal clinical records, including how to locate, organise, and cite relevant evidence across documents.
• Developing XAI tool-using agents.
• Evaluation of explanation reliability and usefulness (incl., human-centred studies of how explanations support understanding and decision-making)

The successful candidates will work in a team together with Wilker Aziz and Vlad Niculae, and two postdocs, within several larger collaboration networks:

• A Horizon Europe consortium with more than a dozen partner institutes from Europe, UK and Canada
• The Language Technology lab at the Informatics Institute at UvA
• The Natural Language Processing unit at the Institute for, Logic, Language, and Computation at UvA
• Potentially, the ELLIS international doctoral network.

• A master’s degree (completed or very near completion) with a thesis in Natural Language Processing, Machine Learning, Computer Science, or similar relevant areas;
• Curiosity and motivation for pursuing fundamental academic research;
• A good background in natural language processing and machine learning;
• Comfort with scientific programming, training ML models.
• Professional command of the English language;
• A commitment to maintaining an inclusive, collaborative, diverse, and supportive work environment.

The Faculty of Science has a student body of around 8,000, as well as 1,800 members of staff working in education, research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works, be it elementary particles, the birth of the universe or the functioning of the brain.

The mission of the Informatics Institute (IvI) is to perform curiosity-driven and use-inspired fundamental research in Computer Science. The main research themes are Artificial Intelligence, Computational Science and Systems and Network Engineering. Our research involves complex information systems at large, with a focus on collaborative, data driven, computational and intelligent systems, all with a strong interactive component.

The Language Technology Lab (LTL) is a research group focusing on information access from natural language data. Our work ranges from basic research in natural language processing to key applications in human language technology, and covers areas such as machine translation, summarization, question answering, language modeling, and image captioning.

The Institute for Logic, Language and Computation (ILLC) is home to a thriving community of scholars, including philosophers, logicians, mathematicians, computer scientists, linguists, musicologists, and cognitive scientists, who share a fascination with the interdisciplinary study of information. At the ILLC we combine the problem-solving skills from the sciences with the holistic and reflective view of the humanities to discover the principles that regulate information processing and find answers to some of the hardest challenges of our time.

One of the PhD positions is formally embedded in the LTL at IvI, and the other in the NLP unit at ILLC. Both will be co-supervised by Wilker Aziz and Vlad Niculae.

Want to know more about our organisation? Read more about working at the University of Amsterdam.

If you feel the profile fits you, and you are interested in the job, we look forward to receiving your application. You can apply online via the red button. We accept applications until and including 06/12/2026 CET.

Applications should include the following information (all files besides your cv should be submitted in one single pdf file):

• a detailed CV including the months (not just years) when referring to your education and work experience;
• a letter of motivation (max 1p, without GenAI writing) explaining your interest in the project, why you are a good fit, how you would approach it, and any constraints on your starting date. 
• a copy of master’s thesis
• a copy of your relevant master’s and bachelor’s transcript/diploma

If your master’s thesis is not in English, provide just a brief abstract. You may provide your own translation or summary of the transcripts in a brief cover page. If your transcripts or diplomas are not available yet, please attach a note clearly stating which documents are not available, and when they will be available. This note can be in your own words.

A knowledge security check can be part of the selection procedure.
(for details: national knowledge security guidelines). 

Only complete applications received within the response period via the link below will be considered.

If you have any questions or do you require additional information? Please send an email, containing the vacancy number in the subject line, to:

• dr. Vlad Niculae, [email protected]
• dr. Wilker Aziz, [email protected]