iiinova — where your digital self keeps evolving

Abdellah Fourtassi

@fourtassi.bsky.social

363 followers 324 following 61 posts

Multimodal Communication and Learning in Social Interactions (CoCoDev team). Associate Professor of Computer/Cognitive Science at Aix-Marseille University. afourtassi.github.io

Posts Replies Media

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

Mechanism 3: response modeling. Children are more contingent for communicative intents that caregivers typically express with short utterances.

110

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

Mechanism 2: interactive routines. Contingency rises sharply when caregivers initiate predictable sequences—such as questions or requests—and children produce the expected response type.

110

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

Mechanism 1: lexical specificity. Children respond more contingently when caregivers use linguistic forms that are more diagnostic of their communicative intent. The pattern is consistent across corpora.

110

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

We test this at scale: 40 CHILDES corpora, 609 children, and 2,577 conversations, focusing on children around 20–32 months.

100

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

Producing a contingent response requires several coordinated steps: decoding the speaker’s intent, selecting an appropriate next intent, and realizing that intent linguistically—all under the time pressure of turn-taking. We ask whether caregivers scaffold each of these steps.

100

Abdellah Fourtassi @fourtassi.bsky.social · 01/09/2026

Happy to share our new paper: "Scaffolding Early Dialogue: A Unified Account of Response Contingency in Child–Caregiver Interaction" with @abhiagrawal.bsky.social and Benoît Favre. Question: How can infants participate in dialogue while their linguistic and cognitive abilities are still immature? 🧵

1102

Abdellah Fourtassi @fourtassi.bsky.social · 08/03/2026

Open PhD/Postdoc position (start: Oct 2026). Topic: AI/LLMs and child language/communicative/cognitive development. The exact project will be shaped with the candidate. Join our team @univ-amu.fr at the intersection of computer and cognitive science (& right next to the Calanques!). Send me your CV!

045

Abdellah Fourtassi @fourtassi.bsky.social · 27/02/2026

Step 2: we use this classifier as the “reward model” in RLHF: a) Train an LLM only on caregiver input (as in Huebner et al., 2021), b) generate an utterance, c) score it with the reward model. A negative reward mean that the utterance is of the kind that would trigger a caregiver CR in CHILDES

110

Abdellah Fourtassi @fourtassi.bsky.social · 27/02/2026

🚨 New Paper: How can AI help us understand child lang dev? If we train models on children’s environment, they can tell us if this environment support learning. E.g., models tested child linguistic input (Huebner et al.) and visual input (Vong et al.). What about Social Interaction? (a thread 🧵)

1235

Abdellah Fourtassi @fourtassi.bsky.social · 20/01/2026

Thrilled to announce the 1st Workshop on Computational Developmental Linguistics (CDL) at ACL 2026 🎉 A new venue at the intersection of development linguistics × modern NLP, spearheaded by @fredashi.bsky.social @marstin.bsky.social, and and outstanding team of colleagues! A thread 🧵

3219

Abdellah Fourtassi @fourtassi.bsky.social · 25/12/2024

I’m excited to announce the release of the special issue "Language Learning, Representation, and Processing in Humans and Machines," that I co-guest edited with Marianna Apidianaki and Sebastian Padó, in Computational Linguistics direct.mit.edu/coli/issue/5...

Thrilled to announce the appearance in Computational Linguistics of the special issue “Language Learning, Representation, and Processing in Humans and Machines,” which I co-edited with Marianna Apidianaki and Sebastian Padó. This issue aimed to compare how humans and LLMs learn, represent, and process language.

1114