| | CoVeGAT: A Hybrid LLM & Graph‑Attention Pipeline for Accurate Citation‑Aligned Claim Verification
Max Bader, Akshatha Arunkumar, Ohan Ahmad, Maruf Hassen, Charles Duong, Vasu Sharma, Sean O’Brien and Kevin Zhu |
| | A Comparative Study of Vision Transformers and Multimodal Language Models for Violence Detection in Videos
Tomas Ditchfield-Ogle and Ruslan Mitkov |
| 16:30–17:00 | Detection of AI-generated Content in Scientific Abstracts
Ernesto Luis Estevanell-Valladares, Alicia Picazo-Izquierdo and Ruslan Mitkov |
| 11:00–11:30 | A Comparative Study of Hyperbole Detection Methods: From Rule-Based Approaches through Deep Learning Models to Large Language Models
Silvia Gargova, Nevena Grigorova and Ruslan Mitkov |
| 11:30–12:00 | Evaluating the Performance of Transformers in Translating Low-Resource Languages through Akkadian
Daniel A. Jones and Ruslan Mitkov |
| | United We Fine-Tune: Structurally Complementary Datasets for Hope Speech Detection
Priya Dharshini Krishnaraj, Tulio Ferreira Leite da Silva, Gonzalo Freijedo Aduna, Samuel Chen, Farah Benamara and Alda Mari |
| | Does Anaphora Resolution Improve LLM Fine-Tuning for Summarisation?
Yi Chun Lo and Ruslan Mitkov |
| | Transformers and Large Language Models for Hope Speech Detection A Multilingual Approach
Diana Patricia Madera-Espíndola, Zoe Caballero-Domínguez, Valeria J. Ramírez-Macías, Sabur Butt and Hector G. Ceballos |
| 12:00–12:30 | Beyond BLEU: Ethical Risks of Misleading Evaluation in Domain-Specific QA with LLMs
Ayoub Nainia, Régine Vignes-Lebbe, Hajar Mousannif and Jihad Zahir |
| | From Zero to Hero: Building Serbian NER from Rules to LLMs
Milica Ikonić Nešić, Sasa Petalinkar, Ranka Stanković and Ruslan Mitkov |
| | Enhancing the Performance of Spoiler Review Detection by a LLM with Hints
Genta Nishi and Einoshin Suzuki |
| | Evaluating Structured Decoding for Text-to-Table Generation: Evidence from Three Datasets
Julian Oestreich and Lydia Müller |
| 17:00–17:30 | Evaluating the LLM and NMT Models in Translating Low-Resourced Languages
Julita JP Pucinskaite and Ruslan Mitkov |
| 15:00–15:30 | KGEIR: Knowledge Graph-Enhanced Iterative Reasoning for Multi-Hop Question Answering
Tianda Sun and Dimitar Kazakov |
| 17:30–18:00 | From Handcrafted Features to LLMs: A Comparative Study in Native Language Identification
Aliyah C. Vanterpool and Katsiaryna Aharodnik |
| 15:30–16:00 | Systematic Evaluation of Rule-Based Analytics for LLM-Driven Graph Data Modelling
Fabio Antonio Yanez, Andrés Montoyo, Armando Suárez, Alejandro Piad-Morffis and Yudivián Almeida Cruz |
| | Improved Contrastive Learning over Commonsense Knowledge Graphs for Unsupervised Reasoning
Rongwen Zhao and Jeffrey Flanigan |
| | TextBandit: Evaluating Probabilistic Reasoning in LLMs Through Language-Only Decision Tasks
Arjun Damerla, Jimin Lim, Yanxi Jiang, Nam Nguyen Hoai Le and Nikil Selladurai |