Papers by Christine Largeron
Are Stereotypes Leading LLMs’ Zero-Shot Stance Detection ? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many tasks. |
| Approach: | They propose to annotate posts in pre-existing stance detection datasets with dialect or vernacular of a specific group and text complexity/readability to investigate whether these attributes influence the model’s stance detect decisions. |
| Outcome: | The proposed model exhibits significant stereotypes when performing stance detection tasks in a zero-shot setting. |
Community Topic: Topic Model Inference by Consecutive Word Community Discovery (2022.coling-1)
Copied to clipboard
| Challenge: | a new topic modelling algorithm is developed to help researchers understand large corpora . community topic can be used to find coherent topics at various scales . |
| Approach: | They propose a topic-modeling algorithm that extracts communities from term co-occurrence networks and compares it with Latent Dirichlet Allocation and top2vec. |
| Outcome: | The proposed algorithm can find coherent topics at various scales. |
SENSE-LM : A Synergy between a Language Model and Sensorimotor Representations for Auditory and Olfactory Information Extraction (2024.findings-eacl)
Copied to clipboard
| Challenge: | SENSE-LM is a system for the extraction of sensory references in textual corpus . it is based on large language models and linguistic resources such as sensorimotor norms . |
| Approach: | They propose a system that extracts sensory references from large corpus of textual documents using large language models and linguistic resources such as sensorimotor norms. |
| Outcome: | The proposed system is evaluated on two sensory functions, Olfaction and Audition, and compared with state-of-the-art methods. |
Unsupervised stance detection for social media discussions: A generic baseline (2024.eacl-long)
Copied to clipboard
| Challenge: | stance detection methods are designed for specific network types, either homophilic or heterophilic, and fail to generalize to both. |
| Approach: | They propose to generalize a graph neural network based on text embeddings to homophilic and homophilic networks. |
| Outcome: | The proposed model outperforms state-of-the-art methods across heterophilic and homophilic networks. |