Papers by Dumitru-Clementin Cercel

8 papers
GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Question answering systems have been used for various domains and languages.
Approach: They propose a novel approach for question answering (QA) that combines a dataset of Romanian legal questions with a CROL corpus of laws.
Outcome: The proposed approach achieves competitive results with generally accepted state-of-the-art methods and even exceeds them in most settings.
Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are popular in the Natural Language Processing community because of their versatility and capability to solve unseen tasks in zero/few-shot settings.
Approach: They investigate the use of large language models in CWI, LCP, and MWE settings by evaluating their use in zero-shot, few-shot and fine-tuning settings.
Outcome: The proposed models struggle in certain conditions or achieve comparable results against existing methods.
MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language (2025.findings-emnlp)

Copied to clipboard

Challenge: MoRoVoc is the largest dataset for analyzing the regional variation of spoken Romanian . it has more than 93 hours of audio and 88,192 audio samples .
Approach: They propose a multi-target adversarial training framework that incorporates demographic attributes as adversarials for speech models.
Outcome: The proposed model achieves 78.21% accuracy for variation identification of spoken Romanian using gender as an adversarial target.
RoQLlama: A Lightweight Romanian Adapted Language Model (2024.findings-emnlp)

Copied to clipboard

Challenge: Currently, open-source large language models are limited to tasks involving the English language.
Approach: They propose to use QLoRA to train a Romanian-adapted LLM with 7 billion parameters and quantized to 4 bits to improve model's performance.
Outcome: The proposed model outperforms the other LLMs on four out of the seven tasks investigated using zero-shot prompting.
Distilling the Knowledge of Romanian BERTs Using Multiple Teachers (2022.lrec-1)

Copied to clipboard

Challenge: Existing approaches to train pre-trained language models focus on the English language, thus widening the gap when considering low-resource languages.
Approach: They propose three versions of distilled BERT models for the Romanian language . they argue that the models offer performance comparable to their teachers .
Outcome: The proposed models perform comparable to their teachers, while being twice as fast on a GPU and 35% smaller.
Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model (D19-50)

Copied to clipboard

Challenge: a new task is needed to detect propaganda in news articles . the need for communication has increased in online social media platforms . a proposed solution to the problem of sentence-level propaganda classification is ranked 12th .
Approach: They propose to build a binary classifier able to provide corresponding propaganda labels . their solution ranks 12th among 26 teams in the NLP4IF-2019 Shared Task SLC .
Outcome: The proposed model outperforms baseline approach and the winning system on a similar task.
RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams (2026.findings-eacl)

Copied to clipboard

Challenge: a growing need for tools that support legal education, especially in under-resourced languages such as Romanian . we evaluate the capabilities of large language models and vision-language models in legal education .
Approach: They evaluate the capabilities of Large Language Models and Vision-Language Models in Romanian driving law through textual and visual question-answering tasks.
Outcome: The proposed model improves retrieval performance and QA accuracy in Romanian driving tests.
RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation (2025.coling-main)

Copied to clipboard

Challenge: Using supervised automatic summarization requires sufficient corpora that include pairs of documents and their summaries.
Approach: They propose a large-scale summarization dataset for the Romanian language that is crawled from publicly available news websites.
Outcome: The proposed system performs well in abstractive summarization, which involves generating new sentences that capture the essence of the original text rather than extracting and rephrasing existing sentences.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations