PhD Position F/M The role of rapport in humanconversational agent interaction: Modeling conversation to improve task performance in humanagent interaction

Download job offer in PDF format

Niveau de diplôme exigé : Graduate degree or equivalent

Autre diplôme apprécié : Ecole d'ingénieur (computer science or engineering degree)

Fonction : Tempary Research Position

Niveau d'expérience souhaité : Recently graduated

Contexte et atouts du poste

The objective of this project is to build embodied conversational agents (also known as ECAs, or virtual humans, or chatbots, or multimodal dialogue systems) that have the ability to engage their users in both social and task talk, where the social talk serves to improve task performance. In order to achieve this objective, we model human-human conversation, and integrate the models into ECAs, and then evaluate their performance.

This project is located at the prestigious computer science institute INRIA in downtown Paris. It takes place in the context of the PRAIRIE Institute for Interdisciplinary Research on AI - one of the four 3IA institutes launched by the French government in 2019. For more information see

<https://www.inria.fr/fr/inria-participe-la-creation-de-linstitut-prairie> and <https://prairie-institute.fr/>

Mission confiée

The doctoral student selected for this project will acquire a broad range of skills in the analysis and synthesis of conversational behavior. They will explore how to enhance the social capabilities of Large Language Models (LLMs) by developing methods for building and maintaining rapport in human-AI interactions. The research will involve building and annotating a corpus focused on the social aspects of human conversation within a specific domain, followed by data analysis to derive computational models informed by both empirical findings and prior literature. These models will be refined and integrated into LLM-based conversational models, with a focus on preserving task performance while enabling socially aware behavior. The developed models will then be integrated into an Embodied Conversational Agent (ECA) to assess their impact on system performance. Potential applications include digital assistants, educational tools, and AI systems in healthcare.

Principales activités

  • Design and carry out experiments
  • Analyze their results
  • Implement modules in working socially-aware dialogue systems
  • Write articles
  • Present work in conferences
  • Write a doctoral thesis

Compétences

Technical skills and level required :

Solid competence in deep learning applied to language (prior experience working with dialogue systems is a strong plus), competence in statistics, avanced competence in programming in language such as Python and C++, and use of tools such as Tensorflow and Pytorch.

Languages :

French and English

Relational skills :

ability to work in a team, and collaborate with others from different disciplines and backgrounds.

Other valued appreciated :

Theoretical background in one or several of the following: cognitive science, linguistics, conversational analysis, sociolinguistics, social cognition, learning science.

Avantages

  • Restauration subventionnée
  • Transports publics remboursés partiellement
  • Congés: 7 semaines de congés annuels + 10 jours de RTT (base temps plein) + possibilité d'autorisations d'absence exceptionnelle (ex : enfants malades, déménagement)
  • Possibilité de télétravail et aménagement du temps de travail
  • Équipements professionnels à disposition (visioconférence, prêts de matériels informatiques, etc.)
  • Prestations sociales, culturelles et sportives (Association de gestion des œuvres sociales d'Inria)
  • Accès à la formation professionnelle
  • Sécurité sociale