Automated Verification of Textual Claims

Informazioni relative al progetto

AVeriTeC

ID dell’accordo di sovvenzione: 865958

DOI

10.3030/865958

Progetto chiuso

Data della firma CE 3 Febbraio 2020

Data di avvio 1 Gennaio 2021

Data di completamento 31 Dicembre 2025

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 982 824,00

Contributo UE

€ 1 982 824,00

Coordinato da

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE
United Kingdom

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (27)

Explainable Assessment of Healthcare Articles with QA

Autori: Alodie Boissonnet, Marzieh Saeidi, Vassilis Plachouras, Andreas Vlachos
Pubblicato in: Proceedings of the 21st Workshop on Biomedical Language Processing, 2022
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.bionlp-1.1

Causal Estimation of Memorisation Profiles

Autori: Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel
Pubblicato in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, Pagina/e 15616-15635
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.acl-long.834

Zero-Shot Fact Verification via Natural Logic and Large Language Models

Autori: Marek Strong, Rami Aly, Andreas Vlachos
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024, Pagina/e 17021-17035
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.findings-emnlp.991

Zero-Shot Fact-Checking with Semantic Triples and Knowledge Graphs

Autori: Moy Yuan, Andreas Vlachos
Pubblicato in: Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024), 2024, Pagina/e 105-115
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.kallm-1.11

PledgeTracker: A System for Monitoring the Fulfilment of Pledges

Autori: Yulong Chen, Michael Sejr Schlichtkrull, Zhenyun Deng, David Corney, Nasim Asl, Joshua Salisbury, Andrew Dudfield, Andreas Vlachos
Pubblicato in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2025, Pagina/e 839-850
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2025.emnlp-demos.64

TSVer: A Benchmark for Fact Verification Against Time-Series Evidence

Autori: Marek Strong, Andreas Vlachos
Pubblicato in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025, Pagina/e 29894-29914
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2025.emnlp-main.1519

FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information

Autori: Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
Pubblicato in: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, 2021
Editore: Neural Information Processing Systems

The Automated Verification of Textual Claims (AVeriTeC) Shared Task

Autori: Michael Schlichtkrull, Yulong Chen, Chenxi Whitehouse, Zhenyun Deng, Mubashara Akhtar, Rami Aly, Zhijiang Guo, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal, James Thorne, Andreas Vlachos
Pubblicato in: Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER), 2024, Pagina/e 1-26
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.fever-1.1

Varifocal Question Generation for Fact-checking

Autori: Nedjma Djouhra Ousidhoum, Zhangdie Yuan, Andreas Vlachos
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Pagina/e 2532--2544
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-main.163

The 2nd Automated Verification of Textual Claims (AVeriTeC) Shared Task: Open-weights, Reproducible and Efficient Systems

Autori: Mubashara Akhtar, Rami Aly, Yulong Chen, Zhenyun Deng, Michael Schlichtkrull, Chenxi Whitehouse, Andreas Vlachos
Pubblicato in: Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), 2025, Pagina/e 201-223
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2025.fever-1.15

Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning

Autori: Zhenyun Deng, Yulong Chen, Andreas Vlachos
Pubblicato in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025, Pagina/e 24783-24799
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2025.emnlp-main.1258

Automated Fact-Checking in Dialogue: Are Specialized Models Needed?

Autori: Eric Chamoun, Marzieh Saeidi, Andreas Vlachos
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, Pagina/e 16009-16020
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.993

AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web

Autori: Zhijiang Guo, Michael Schlichtkrull, Andreas Vlachos
Pubblicato in: Advances in Neural Information Processing Systems 36, 2026, Pagina/e 65128-65167
Editore: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/075280-2842

Evidence-based Factual Error Correction

Autori: Thorne, James and Vlachos, Andreas
Pubblicato in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers, 2021
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-long.256

Elastic weight consolidation for better bias inoculation

Autori: Thorne, James and Vlachos, Andreas
Pubblicato in: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 2021
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.eacl-main.82

Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification

Autori: Rami Aly, Andreas Vlachos
Pubblicato in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, Pagina/e 6123--6135
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2022.emnlp-main.411

QA-NatVer: Question Answering for Natural Logic-based Fact Verification

Autori: Rami Aly, Marek Strong, Andreas Vlachos
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, Pagina/e 8376-8391
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.521

The Intended Uses of Automated Fact-Checking Artefacts: Why, How and Who

Autori: Michael Schlichtkrull, Nedjma Ousidhoum, Andreas Vlachos
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, Pagina/e 8618-8642
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-emnlp.577

FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information

Autori: Rami Aly; Zhijiang Guo; Michael Sejr Schlichtkrull; James Thorne; Andreas Vlachos 0001; Christos Christodoulopoulos 0001; Oana Cocarascu; Arpit Mittal
Pubblicato in: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, Numero 1, 2021
Editore: Curran Associates
DOI: 10.48550/arxiv.2106.05707

Multimodal Automated Fact-Checking: A Survey

Autori: Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, Pagina/e 5430-5448
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.findings-emnlp.361

AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets

Autori: Pietro Lesci, Andreas Vlachos
Pubblicato in: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024, Pagina/e 8445-8464
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.naacl-long.467

Document-level Claim Extraction and Decontextualisation for Fact-Checking

Autori: Zhenyun Deng, Michael Schlichtkrull, Andreas Vlachos
Pubblicato in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, Pagina/e 11943-11954
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.acl-long.645

Tending Towards Stability: Convergence Challenges in Small Language Models

Autori: Richard Diehl Martinez, Pietro Lesci, Paula Buttery
Pubblicato in: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024, Pagina/e 3275-3286
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.findings-emnlp.187

ALVIN: Active Learning Via INterpolation

Autori: Michalis Korakakis, Andreas Vlachos, Adrian Weller
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, Pagina/e 22715-22728
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2024.emnlp-main.1265

The Fact Extraction and VERification Over Unstructured and Structuredinformation (FEVEROUS) Shared Task

Autori: Rami Aly, Zhijiang Guo, Michael Sejr Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
Pubblicato in: Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 2021
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.fever-1.1

Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification

Autori: Rami Aly, Andreas Vlachos, Ryan McDonald
Pubblicato in: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2021.acl-long.120

Improving the robustness of NLI models with minimax training

Autori: Michalis Korakakis, Andreas Vlachos
Pubblicato in: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, Pagina/e 14322–14339
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-long.801

Peer reviewed articles (6)

TabVer: Tabular Fact Verification with Natural Logic

Autori: Rami Aly, Andreas Vlachos
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 12, 2024, Pagina/e 1648-1671, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/tacl_a_00722

Disinformation 2.0 in the Age of AI: A Cybersecurity Perspective

Autori: Wojciech Mazurczyk, Dongwon Lee, Andreas Vlachos
Pubblicato in: Communications of the ACM, Numero 67, 2025, Pagina/e 36-39, ISSN 0001-0782
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3624721

ProoFVer: Natural Logic Theorem Proving for Fact Verification

Autori: Amrith Krishna, Sebastian Riedel, Andreas Vlachos
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 10, 2022, Pagina/e 1013–1030, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/tacl_a_00503

<scp>AmbiFC</scp>: Fact-Checking Ambiguous Claims with Evidence

Autori: Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 12, 2024, Pagina/e 1-18, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/tacl_a_00629

A Survey on Automated Fact-Checking

Autori: Zhijiang Guo, Michael Schlichtkrull, Andreas Vlachos
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 2307387X, 2022, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/tacl_a_00454

Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking

Autori: Mubashara Akhtar, Michael Schlichtkrull, Andreas Vlachos
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 14, 2026, Pagina/e 530-561, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/tacl.a.647