activity
20242026
collaborators

10 papers

cs.CL2026

ReLTEx: Reliable LLM-based Taxonomy Expansion

Zeinab Ghamlouch, Mehwish Alam

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for ta…

cs.CL2026

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Ngoc Trinh Hung Nguyen, Alonso Silva, Laith Zumot +3

Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely,…

cs.CL2026

DELICATE: Diachronic Entity LInking using Classes And Temporal Evidence

Cristian Santini, Sebastian Barzaghi, Paolo Sernani +2

In spite of the remarkable advancements in the field of Natural Language Processing, the task of Entity Linking (EL) remains challenging in the field of humanities due to complex d…

cs.CL2026

ENEIDE: A High Quality Silver Standard Dataset for Named Entity Recognition and Linking in Historical Italian

Cristian Santini, Sebastian Barzaghi, Paolo Sernani +3

This paper introduces ENEIDE (Extracting Named Entities from Italian Digital Editions), a silver standard dataset for Named Entity Recognition and Linking (NERL) in historical Ital…

cs.CL2026

Analysing Lightweight Large Language Models for Biomedical Named Entity Recognition on Diverse Ouput Formats

Pierre Epron, Adrien Coulet, Mehwish Alam

Despite their strong linguistic capabilities, Large Language Models (LLMs) are computationally demanding and require substantial resources for fine-tuning, which is unadapted to pr…

cs.CL2026

It's All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models

Cristian Santini, Marieke Van Erp, Mehwish Alam

Despite the recent advancements in NLP with the advent of Large Language Models (LLMs), Entity Linking (EL) for historical texts remains challenging due to linguistic variation, no…