AIConfPaper
← Search

Karl Aberer

5 accepted papers

2025

WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts

Negar Foroutan, Angelika Romanou, Matin Ansaripour, Julian Martin Eisenschlos, Karl Aberer, Rémi Lebret
ACL 2025finding

Documents are fundamental to preserving and disseminating information, often incorporating complex layouts, tables, and charts that pose significant challenges for automatic document understanding (DU). While vision-language large models (VLLMs) have demonstrated improvements across various tasks, t…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2023

Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention

Negar Foroutan, Mohammadreza Banaei, Karl Aberer, Antoine Bosselut
EMNLP 2023long findings

In this work, we study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We evaluate the cross-lingual reasoning abilities of MultiLMs in two schemes: (1) where the language of t…

Cited by 0Source ↗code ↗Scholar ↗
2023

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events

Angelika Romanou, Syrielle Montariol, Debjit Paul, Leo Laugier, Karl Aberer, Antoine Bosselut
EMNLP 2023long main

Understanding narratives requires reasoning about the cause-and-effect relationships between events mentioned in the text. While existing foundation models yield impressive results in many NLP tasks requiring reasoning, it is unclear whether they understand the complexity of the underlying network o…

Cited by 0Source ↗code ↗Scholar ↗
2023

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Yasmine Karoui, Rémi Lebret, Negar Foroutan Eghlidi, Karl Aberer
ACL 2023short

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous work has demonstrated that the pre-training…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2022

Discovering Language-neutral Sub-networks in Multilingual Language Models

Negar Foroutan, Mohammadreza Banaei, Rémi Lebret, Antoine Bosselut, Karl Aberer
EMNLP 2022main

Multilingual pre-trained language models transfer remarkably well on cross-lingual downstream tasks. However, the extent to which they learn language-neutral representations (i.e., shared representations that encode similar phenomena across languages), and the effect of such representations on cross…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗