List of Talks and Posters:

Wissam Antoun (Inria Paris):  LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse Autoencoders (EMNLP 2026)

Tian Fang (LIPN, Université Sorbonne Paris Nord): Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models (EMNLP 2026)

Pierre Fihey (Télécom Paris): A Geometry-Aware Depth Function for Robust Unsupervised Textual Anomaly Detection (EMNLP 2026)

Mingmeng Geng (Lattice, ENS-PSL): Markovian Generation Chains in Large Language Models (EMNLP 2026)

Mingmeng Geng (Lattice, ENS-PSL): The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs (EMNLP 2026)

Francis Kulumba (Inria Paris, Sorbonne Université): HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction (EMNLP 2026)

Victor Morand (ISIR - Sorbonne University): MICE: Minimal Interaction Cross-Encoders for efficient Re-ranking (EMNLP 2026)

Anna Mosolova (Inria Paris): When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs (EMNLP 2026)

Michel Olvera (Télécom Paris): Probing large audio-language models for compositional understanding of sounding actions (EMNLP 2026)

Joanna Radoła (ISIR - Sorbonne University): Improving Language Identification for Code-Switched Utterances with Integer Linear Programming (EMNLP 2026)

Amine Youcef Khodja (Greyc - Université Caen Normandie): Anomaly Detection using Source-Reversed Flow Matching (EMNLP 2026)

Guy Stéphane Waffo Dzuyo (Université de Lorraine, Loria, Forvis Mazars): Forensic Bench : Evaluating Agentic LLMs on Journal-Entry Fraud Detection (EMNLP 2026)

Chenwei Wan (SLB): Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents (EMNLP 2026)

Kun Zhang (CNRS/LORIA, Université de Lorraine): Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data (EMNLP 2026)

Kun Zhang (CNRS/LORIA, Université de Lorraine): XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals (EMNLP 2026)

Rowan Hall Maudslay (CultureLab, PSL): Simulating Sense Extension (TACL 2026)

Akram Elbouanani (Cea-List): A Scalable Entity-Based Framework for Auditing Bias in LLMs (ACL 2026)*

Nisrine Rair (Université de Reims champagne Ardenne): Beyond Black-Box Labels: Interpretable Criteria for Diagnosing Subjective NLP Tasks (ACL 2026)*

Luc Pommeret (LISN, Université Paris Saclay): Can We Do Interpretable NLI with Graphs Based on Atomic Propositions? (EMNLP 2026 Automated Knowledge Base Construction workshop)

Justine Reverdy (Inria Paris): Validation of a Multi-level Self-Report Rapport Scale and its impact on Multimodal Modeling of Small Group Interaction (ICMI 2026)

Nicolas Turenne (INRAE & UMMISCO IRD Sorbonne Université): An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts (SEKE 2026 Software Engineering Knowledge Engineering)

*Being a pre-conference event, we give priority to upcoming conference papers, but recently accepted work is also welcome if space allows.