activity
20182025
most citedSemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)

16 citations · 20 across the 8 of their papers we have counts for

collaborators

16 papers

cs.CL2025

Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models

Jingyi Sun, Pepa Atanasova, Sagnik Ray Choudhury +2

Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, remains largely opaque to users,…

cs.CL2025

Self-Critique and Refinement for Faithful Natural Language Explanations

Yingming Wang, Pepa Atanasova

With the rapid development of Large Language Models (LLMs), Natural Language Explanations (NLEs) have become increasingly important for understanding model predictions. However, th…

cs.CY2025

Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation

Lucie-Aimée Kaffee, Pepa Atanasova, Anna Rogers

The rapid adoption of AI across diverse domains has led to the development of organisational guidelines that vary significantly, even within the same sector. This paper examines AI…

cs.CL2024

A Reality Check on Context Utilisation for Retrieval-Augmented Generation

Lovisa Hagström, Sara Vera Marjanović, Haeun Yu +5

Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can…

cs.CL2024

Graph-Guided Textual Explanation Generation Framework

Shuzhou Yuan, Jingyi Sun, Ran Zhang +4

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned…

cs.LG20222 cited

Accountable and Explainable Methods for Complex Reasoning over Text

Pepa Atanasova

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not prov…