Thematic Axis: NLP & LLMs
Leader(s)
Mailing list
In order to get information about the WG activities, you can subscribe to its mailing list at https://sympa.inria.fr/sympa/info/mosaiknlp.
Description
Members of the MosAIk team working on the Natural Language Processing & Large Language Models (NLP & LLMs) axis share a common interest in textual data. Their activities belong to the following axes :
- research work focussing either on LLMs themselves, or on the use of LLMs in the context of NLP applications ;
- research work focussing on multimodal deep learning models ;
- research work focussing on (deep and non-deep) Machine Learning techniques applied on texts ;
- research work focussing on NLP applications.
Current activities include LLM compression, (multilingual) text generation, merging of knowledge-based information and LLMs in the context of hybrid AI, federating learning techniques, and NLP applications such as literature analysis or Computer-Assisted Language Learning.
The main objectives in relation to this axis is to provide researchers with a space to facilitate cooperation on the topics mentioned above, e.g. by sharing expertise and / or code.
Organisation
We propose to organise our work within “focal groups”, which are even totally bottom-up and free to “create”, self-organize and disappear. Focal groups are typically composed of 2 to 6 members who have decided to work or study together some precise topic related to LLM.
Team Team axes Focal groups Topic Contact
┌────────┐ ┌─────┐ ┌───────┐
│ Mosaik ├─────┬───────┤ NLP ├───────┬──────┤ LLM42 │ LLM internals Christophe Cerisara
└────────┘ │ └─────┘ │ └───────┘
│ │ ┌───────┐
│ ├──────┤Review │ Lit. review Barbara Gendron
│ │ └───────┘
│ │ ┌───────┐
│ └──────┤ Philo │ Reasoning David Langlois
│ └───────┘
│ ┌────────┐
├───────┤ Frugal │
│ └────────┘
│
│
│ ┌─────┐
└─────────┤ ... │
└─────┘