Explainable and Robust Automatic Fact Checking

Informacje na temat projektu

ExplainYourself

Identyfikator umowy o grant: 101077481

DOI

10.3030/101077481

Data podpisania przez KE 17 Grudnia 2022

Data rozpoczęcia 1 Września 2023

Data zakończenia 31 Sierpnia 2028

Finansowanie w ramach

• European Research Council (ERC)

Koszt całkowity

€ 1 498 616,00

Wkład UE

€ 1 498 616,00

Koordynowany przez

KOBENHAVNS UNIVERSITET
Denmark

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Publikacje

Conference proceedings (15)

Explaining Interactions Between Text Spans

Autorzy: Sagnik Choudhury, Pepa Atanasova, Isabelle Augenstein
Opublikowane w: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2023.EMNLP-MAIN.783

Can Community Notes Replace Professional Fact-Checkers?

Autorzy: Nadav Borenstein, Greta Warren, Desmond Elliott, Isabelle Augenstein
Opublikowane w: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-SHORT.42

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework

Autorzy: Jingyi Sun, Pepa Atanasova, Isabelle Augenstein
Opublikowane w: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2025
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2025.NAACL-LONG.530

Faithfulness Tests for Natural Language Explanations

Autorzy: Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, Thomas Lukasiewicz, Jakob Grue Simonsen, Isabelle Augenstein
Opublikowane w: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2023.ACL-SHORT.25

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods

Autorzy: Yu, Haeun; Atanasova, Pepa; Augenstein, Isabelle
Opublikowane w: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
Wydawca: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2404.18655

Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

Autorzy: Kevin Roitero, Dustin Wright, Michael Soprano, Isabelle Augenstein, Stefano Mizzaro
Opublikowane w: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2025
Wydawca: ACM
DOI: 10.1145/3726302.3729960

Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers

Autorzy: Yuxia Wang, Revanth Gangi Reddy, Zain Muhammad Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, Isabelle Augenstein, Iryna Gurevych, Preslav Nakov
Opublikowane w: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-EMNLP.830

A Reality Check on Context Utilisation for Retrieval-Augmented Generation

Autorzy: Lovisa Hagström, Sara Vera Marjanovic, Haeun Yu, Arnav Arora, Christina Lioma, Maria Maistro, Pepa Atanasova, Isabelle Augenstein
Opublikowane w: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-LONG.968

Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking

Autorzy: Greta Warren; Irina Shklovski; Isabelle Augenstein
Opublikowane w: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, 2025
DOI: 10.48550/ARXIV.2502.09083

SynDARin: Synthesising Datasets for Automated Reasoning in Low-Resource Languages

Autorzy: Gayane Ghazaryan, Erik Arakelyan, Isabelle Augenstein, Pasquale Minervini
Opublikowane w: Proceedings of the 31st International Conference on Computational Linguistics, 2025
Wydawca: Association for Computational Linguistics

Investigating the Impact of Model Instability on Explanations and Uncertainty

Autorzy: Sara Marjanovic, Isabelle Augenstein, Christina Lioma
Opublikowane w: Findings of the Association for Computational Linguistics ACL 2024, 2024
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-ACL.705

Measuring and Benchmarking Large Language Models’ Capabilities to Generate Persuasive Language

Autorzy: Amalie Brogaard Pauli, Isabelle Augenstein, Ira Assent
Opublikowane w: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2025
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2025.NAACL-LONG.506

LLM Tropes: Revealing Fine-Grained Values and Opinions in Large Language Models

Autorzy: Dustin Wright, Arnav Arora, Nadav Borenstein, Srishti Yadav, Serge Belongie, Isabelle Augenstein
Opublikowane w: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2024.FINDINGS-EMNLP.995

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection

Autorzy: Indira Sen, Dennis Assenmacher, Mattia Samory, Isabelle Augenstein, Wil Aalst, Claudia Wagner
Opublikowane w: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Wydawca: Association for Computational Linguistics
DOI: 10.18653/V1/2023.EMNLP-MAIN.649

DYNAMICQA:Tracing Internal Knowledge Conflicts in Language Models

Autorzy: Marjanović, Sara Vera; Yu, Haeun; Atanasova, Pepa; Maistro, Maria; Lioma, Christina; Augenstein, Isabelle
Opublikowane w: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
DOI: 10.18653/V1/2024.FINDINGS-EMNLP.838

Peer reviewed articles (1)

Factuality challenges in the era of large language models and opportunities for fact-checking

Autorzy: Isabelle Augenstein; Timothy Baldwin; Meeyoung Cha; Tanmoy Chakraborty; Giovanni Luca Ciampaglia; David Corney; Renee DiResta; Emilio Ferrara; Scott Hale; Alon Halevy; Eduard Hovy; Heng Ji; Filippo Menczer; Ruben Miguez; Preslav Nakov; Dietram Scheufele; Shivam Sharma; Giovanni Zagni
Opublikowane w: Nature Machine Intelligence, 2024, ISSN 2522-5839
Wydawca: Nature
DOI: 10.1038/S42256-024-00881-Z