About the Event

We hope to establish a regular series of one-day meetings in Paris, bringing together NLP researchers from the Paris community and beyond to share research, stimulate discussion, and build collaborations.

Venue and Registration

The Pre-Conference will be held on March 18, 2026, at Salle Dussane, École normale supérieure (45 Rue d'Ulm, 75005 Paris).

The event is free of charge, but registration in advance is required.

Papers and Presentations

We welcome presentations of papers accepted to:

EACL 2026 (including Findings)
EACL 2026 Workshops
ICLR 2026 (NLP-related papers only)

Additionally, if time and space permit, we may also accommodate:

Recent journal publications in NLP (TACL, TMLR, etc.)
Recent papers from other major conferences

This Pre-Conference will take place from 9:30 AM to 5:00 PM. Coffee breaks will be provided, but participants should arrange their own lunch.

The speakers and papers are as follows:

9h00		Gates Open
9h30		Welcoming Notes
9h50	Léo Labat	Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions (EACL 2026)
10h10	Mingmeng Geng	code_transformed: The Influence of Large Language Models on Code (EACL 2026)
	Noé Durandard	Evaluating Style Embeddings for Machine-Generated Text Detection (LREC 2026)
10h25		Coffee Break (Offered by the Lattice)
11h00	Arthur Satouf	QueStER: Query Specification for Generative keyword-based Retrieval (EACL 2026)
11h20	Ayoub Hammal	Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral (EACL 2026)
11h40	Loïc Fosse	DivMerge: A divergence-based model merging method for multi-tasking (EACL 2026)
12h00		Lunch (Not Provided)
14h00	Pierre-Carl Langlais	Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training (ICLR 2026)
14h20	Arij Riabi	IYKYK: Using language models to decode extremist cryptolects (EACL 2026)
14h40	Yongxin Zhou	What Matters to an LLM? Behavioral and Computational Evidences from Summarization (EACL 2026)
15h00	Yang Zhang	Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning (EACL 2026)
	Syrielle Montariol	DrivingVQA: A Dataset for Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios (EACL 2026)
	Arij Riabi	The Anthropology of Food: How NLP can Help us Unravel the Food Cultures of the World (EACL 2026 Workshop)
15h20		Coffee Break (Offered by the Lattice)
16h00		Panel (Frédéric Béchet, Géraldine Damnati, Pierre-Carl Langlais, Olga Seminck)
17h00		Closing Notes

Organizers

Frédéric Béchet (LIS, AMU)
Antoine Bourgois (LATTICE, CNRS, ENS-PSL)
Mathieu Dehouck (LATTICE, CNRS, ENS-PSL)
Mingmeng Geng (LATTICE, CNRS, ENS-PSL)
Amr Mohamed (MBZUAI Paris & LIX, Ecole Polytechnique)
Joanna Radoła (ISIR, Sorbonne)

With support from GDR Traitement Automatique des Langues and Laboratoire Lattice

Contact: paris-nlp-03-26 AT sciencesconf.org