Aarhus University Seal

Reasoning with Large Language Models

Applications are invited for a PhD fellowship/scholarship at Graduate School of Natural Sciences, Aarhus University, Denmark, within the Computer Science programme. The position is available from August 2025 or later.

Title:
Reasoning with Large Language Models

Research area and project description:
With strong reasoning and problem-solving abilities, large language models (LLMs) such as GPT-4, LLaMA, and PaLM have sparked a new-found interest in building general-purpose autonomous agents. LLM-based agents have portrayed excellent performance on reasoning and knowledge-intensive tasks, often requiring interactions with complex environments, such as playing complex video games, performing web navigation, or enabling tool-use.

The overarching goal of this PhD project is to push the state-of-the-art in reasoning with LLMs. Key activities of the project will include devising challenging benchmark datasets and novel reasoning frameworks that improve the cost-quality trade-off of LLM-based reasoning.

The successful candidate will join the CLAN for AI Research on Language and Networks, or “CLAN” for short, headed by Prof. Akhil Arora, Department of Computer Science, Aarhus University (AU). CLAN researchers have extensive experience with LLMs and possess strong collaborations with industrial research labs, such as Wikimedia Foundation and Microsoft Research.

In addition to the usual required documents, a complete application should contain the following:

  • Motivation letter (up to 1 page): explaining your general motivation to do a PhD.
  • Statement of purpose (2-3 pages): explaining your motivation to do a PhD at AU-CLAN, contextualizing your qualifications/background with the call, and a short PhD proposal. This document will serve as your project description.
  • Three letter of recommendations

Qualifications and specific competences:
We are looking for candidates with a Master’s degree in computer science or a closely related field, with a strong profile showcasing mathematical and algorithmic skills. Moreover, we will also consider candidates with a degree in basic sciences (e.g. Math, Physics, etc.) who have portrayed solid background in machine learning and natural language processing. Strong students with a Bachelor’s degree are also considered.

Place of employment and place of work:
The place of employment is Aarhus University, and the place of work is Aabogade 34, 8200 Aarhus N, Denmark. 

Contacts:
For any questions, please contact: akhil.arora@cs.au.dk with the subject “Inquiries: PhD Position on LLM-based Reasoning” (not following the instructions may lead to slow or no responses to your email).

How to apply:

For information about application requirements and mandatory attachments, please see the Application guide. Please read the Application guide thoroughly before applying.

When ready to apply, go to https://phd.nat.au.dk/for-applicants/apply-here/ (Note, the online application system opens 1 March 2025)

  1. Choose May 2025 Call with deadline 1 May 2025 at 23:59 CEST.
  2. You will be directed to the call and must choose the programme “Computer Science”.
  3. In the boxed named “Study”: In the dropdown menu, please choose: “Reasoning with Large Language Models (ReLLaM)”

Please note:

  • The programme committee may request further information or invite the applicant to attend an interview.

At the Faculty of Natural Science at Aarhus University, we strive to support our scientific staff in their career development. We focus on competency development and career clarification and want to make your opportunities transparent. On our website, you can find information on all types of scientific positions, as well as the entry criteria we use when assessing candidates. You can also read more about how we can assist you in your career planning and development.

Aarhus University’s ambition is to be an attractive and inspiring workplace for all and to foster a culture in which each individual has opportunities to thrive, achieve and develop. We view equality and diversity as assets, and we welcome all applicants. All interested candidates are encouraged to apply, regardless of their personal background.

29464 / i43