Internship - Formal reasoning examples generation for large language model training (M/F)

The  Inria University of Lille centre, created in 2008, employs 360 people  including 305 scientists in 15 research teams. Recognised for its strong  involvement in the socio-economic development of the Hauts-De-France  region, the Inria University of Lille centre pursues a close  relationship with large companies and SMEs. By promoting synergies  between researchers and industrialists, Inria participates in the  transfer of skills and expertise in digital technologies and provides  access to the best European and international research for the benefit  of innovation and companies, particularly in the region.For more  than 10 years, the Inria University of Lille centre has been located at  the heart of Lille's university and scientific ecosystem, as well as at  the heart of Frenchtech, with a technology showroom based on Avenue de  Bretagne in Lille, on the EuraTechnologies site of economic excellence  dedicated to information and communication technologies (ICT)

Large Language Models (LLMs) are trained to predict missing words in many situations, which leads them to absorb knowledge, natural language structure, and some (brittle) algorithmic problem- resolution capabilities.
By contrast, symbolic AI matured efficient algorithms to reliably solve various narrow problems (first order logic, modal logics, planning, constraint satisfation...), but it is challenging to successfully apply them in real world problems requiring natural language understanding and knowledge that is hard to formalize.

The goal of the Adada project is to construct reasoning examples to infuse symbolic AI into large language models. To do so, we will formalize a general problem generation framework and instantiate multiple type of symbolic problems generators. We will use existing symbolic solvers to obtain solutions and fine-tune language models to match the solver ouputs.
We will start problem generations using simple grammars (e.g. context free grammars). However, most generated problems will be junk (intractable, redundant, or trivial problems). To address this, we will define the desirable properties of generated problems, and we will steer problem generations toward desirable problems with machine learning techniques (guided generation, efficient language models).
This will enable an adaptive dataset generation, that will prevent dataset obsolescence and personalize dataset generation to specific applications or to specific models (newer/larger models need harder tasks).

Interns will work on dataset generation on a specific topic that depends on their interests, which can include: Modal logic or non standard-logic, planning, first order logic with external knowledge, mathematics (with Lean), formal language processing (grammar induction), symbolic regression, simple visual reasoning.

• Survey existing research
• Construct synthetic dataset generators
• Evaluate LLM on them (zero-shot and after fine-tuning)

• Python
• English (french optional)
• Solid background on formal reasoning (symbolic AI) or math/probability theory
• Language interest (formal semantics appreciated)

"LLMs skills" are not enough and not mandatory, this position is mostly about formal semantics and formal reasoning applied to LLMs

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage