Pepa Atanasova

Assistant Professor (Tenure Track)

Department of Computer Science

Publications

3,359

Citations

46

Publications

24

h-index

Jingyi Sun, Pepa Atanasova, Sagnik Ray Choudhury, Sekh Mainul Islam, Isabelle Augenstein. Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models. Computational Linguistics, 2026

Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein. Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement. arXiv, 2025

Yingming Wang, Pepa Atanasova. Self-Critique and Refinement for Faithful Natural Language Explanations. EMNLP 2025

Shuzhou Yuan, Jingyi Sun, Ran Zhang, Michael Färber, Steffen Eger, Pepa Atanasova, Isabelle Augenstein. Graph-Guided Textual Explanation Generation Framework. EMNLP 2025

Lovisa Hagström, Sara Vera Marjanović, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro, Pepa Atanasova, Isabelle Augenstein. A Reality Check on Context Utilisation for Retrieval-Augmented Generation. ACL 2025

Jingyi Sun, Pepa Atanasova, Isabelle Augenstein. Evaluating Input Feature Explanations Through a Unified Diagnostic Evaluation Framework. NAACL 2025

Lucie-Aimée Kaffee, Pepa Atanasova, Anna Rogers. Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation. NeurIPS 2025

Sara Vera Marjanović, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, Isabelle Augenstein. DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models. EMNLP 2024

Haeun Yu, Pepa Atanasova, Isabelle Augenstein. Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods. ACL 2024

Sagnik Ray Choudhury, Pepa Atanasova, Isabelle Augenstein. Explaining Interactions Between Text Spans. EMNLP 2023 [Code]

Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, Thomas Lukasiewicz, Jakob Grue Simonsen, Isabelle Augenstein. Faithfulness Tests for Natural Language Explanations. ACL 2023 [Code]

Momchil Hardalov, Pepa Atanasova, Todor Mihaylov, Galia Angelova, Kiril Simov, Petya Osenova, et al. bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark. ACL 2023 [Benchmark]

Pepa Atanasova. Accountable and Explainable Methods for Complex Reasoning over Text. PhD Thesis, 2022

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein. Fact Checking with Insufficient Evidence. TACL 2022

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein. Diagnostics-Guided Explanation Generation. AAAI 2022

Luna De Bruyne, Pepa Atanasova, Isabelle Augenstein. Joint Emotion Label Space Modelling for Affect Lexica. Computer Speech & Language, 2022

Shailza Jolly, Pepa Atanasova, Isabelle Augenstein. Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing. Information, 2022

Wojciech Ostrowski, Arnav Arora, Pepa Atanasova, Isabelle Augenstein. Multi-Hop Fact Checking of Political Claims. IJCAI 2021 [Dataset]

Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, Marcos Zampieri, Preslav Nakov. SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification. Findings of ACL 2021

Marcos Zampieri, Preslav Nakov, Sara Rosenthal, Pepa Atanasova, Georgi Karadzhov, et al. SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020). SemEval 2020

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein. A Diagnostic Study of Explainability Techniques for Text Classification. EMNLP 2020 [Code]

Pepa Atanasova*, Dustin Wright*, Isabelle Augenstein. Generating Label Cohesive and Well-Formed Adversarial Claims. EMNLP 2020 [Code]

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein. Generating Fact Checking Explanations. ACL 2020

Pepa Atanasova, Preslav Nakov, Lluís Màrquez, Alberto Barrón-Cedeño, Georgi Karadzhov, Tsvetomila Mihaylova, Mitra Mohtarami, James Glass. Automatic Fact-Checking Using Context and Discourse Information. JDIQ 2019

Tsvetomila Mihaylova, Georgi Karadzhov, Pepa Atanasova, Ramy Baly, Mitra Mohtarami, Preslav Nakov. SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums. SemEval 2019

Tamer Elsayed, Preslav Nakov, Alberto Barrón-Cedeño, Maram Hasanain, et al. Overview of the CLEF-2019 CheckThat! Lab: Automatic Identification and Verification of Claims. CLEF 2019

Slavena Vasileva, Pepa Atanasova, Lluís Màrquez, Alberto Barrón-Cedeño, Preslav Nakov. It Takes Nine to Smell a Rat: Neural Multi-task Learning for Check-worthiness Prediction. RANLP 2019

Preslav Nakov, Alberto Barrón-Cedeño, Tamer Elsayed, Reem Suwaileh, Lluís Màrquez, et al. Overview of the CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims. CLEF 2018

Israa Jaradat, Pepa Atanasova, Alberto Barrón-Cedeño, Lluís Màrquez, Preslav Nakov. ClaimRank: Detecting Check-worthy Claims in Arabic and English. NAACL 2018

Georgi Karadzhov, Pepa Atanasova, Preslav Nakov, Ivan Koychev. We Built a Fake News & Click-bait Filter: What Happened Next Will Blow Your Mind! RANLP 2018

Pepa Atanasova, Preslav Nakov, Lluís Màrquez, Alberto Barrón-Cedeño, Ivan Koychev. A Context-aware Approach for Detecting Worth-checking Claims in Political Debates. RANLP 2017

Tsvetomila Mihaylova, Pepa Atanasova, Momchil Boyanov, et al. SUper Team at SemEval-2016 Task 3: Building a Feature-Rich System for Community Question Answering. SemEval 2016 - First Place