Publications

2024

• Block Transformer: Global-to-Local Language Modeling for Fast Inference
  

  Namgyu Ho, Sangmin Bae, Taehyeon Kim, Hyunjik Jo, Yireun Kim, Tal Schuster, Adam Fisch, James Thorne, Se-Young Yun
  NeurIPS 2024

• ORPO: Monolithic Preference Optimization without Reference Model
  

  Jiwoo Hong, Noah Lee, James Thorne
  EMNLP 2024

• Stable Language Model Pre-training by Reducing Embedding Variability
  

  Woojin Chung, Jiwoo Hong, Na Min An, James Thorne, Se-Young Yun
  EMNLP 2024

• Epistemology of Language Models: Do Language Models Have Holistic Knowledge?
  

  Minsu Kim, James Thorne
  Findings of ACL 2024

• ProbGate at EHRSQL 2024: Enhancing SQL Query Generation Accuracy through Probabilistic Threshold Filtering and Error Handling
  

  Sangryul Kim, Donghee Han, Sehyun Kim
  The 6th Clinical Natural Language Processing Workshop at NAACL 2024

• CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean
  

  Eunsu Kim, Juyoung Suk, Philhoon Oh, Haneul Yoo, James Thorne, Alice Oh
  LREC-COLING 2024

• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
  

  Seungone Kim*, Jamin Shin*, Yejin Cho*, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, Minjoon Seo
  ICLR 2024

• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
  

  Seonghyeon Ye*, Doyoung Kim*, Sungdong Kim, Hyeonbin Hwang, Seungone Kim, Yongrae Jo, James Thorne, Juho Kim, Minjoon Seo
  ICLR 2024 (Spotlight)

• Re3val: Reinforced and Reranked Generative Retrieval
  

  Euiyul Song, Sangryul Kim, Haeju Lee, Joonkee Kim, James Thorne
  Findings of EACL 2024

• Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings
  

  Na Min An, Sania Waheed, James Thorne
  Findings of EACL 2024

2023

• Can Large Language Models Capture Dissenting Human Voices?
  

  Noah Lee*, Na Min An*, James Thorne
  EMNLP 2023

• HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
  

  Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, Se-Young Yun
  Findings of EMNLP 2023

• Detrimental Contexts in Open-Domain Question Answering
  

  Philhoon Oh, James Thorne
  Findings of EMNLP 2023

• Knowledge Corpus Error in Question Answering
  

  Yejoon Lee, Philhoon Oh, James Thorne
  Findings of EMNLP 2023

• Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy
  

  Jiwoo Hong, Yejin Cho, Jaemin Jung, Jiyoung Han, James Thorne
  Findings of EMNLP 2023

• VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual Perception
  

  Jiyoung Lee, Seungho Kim, Seunghyun Won, Joonseok Lee, Marzyeh Ghassemi, James Thorne, Jaeseok Choi, O-Kil Kwon, Edward Choi
  NeurIPS 2023 Datasets and Benchmarks Track

• AmbiFC: Fact-Checking Ambiguous Claims with Evidence
  

  Max Glockner, Ieva Staliūnaitė, James Thorne, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
  TACL 2023

• FactKG: Fact Verification via Reasoning on Knowledge Graphs
  

  Jiho Kim, Sungjin Park, Yeonsu Kwon, Yohan Jo, James Thorne, Edward Choi
  ACL 2023

2022

• Data-efficient Autoregressive Document Retrieval for Fact Verification
  

  James Thorne
  SustaiNLP workshop at EMNLP 2022

• On the Role of Relevance in Natural Language Processing Tasks
  

  Artsiom Sauchuk, James Thorne, Alon Halevy, Nicola Tonellotto, Fabrizio Silvestri
  SigIR 2022

2021

• FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information
  

  Rami Aly, Zhijiang Guo, Michael Schlichtkrull, James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal
  NeurIPS 2021

• Evidence-based Factual Error Correction
  

  James Thorne, Andreas Vlachos
  ACL 2021
  Code
  Data

• Database Reasoning over Text
  

  James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy
  ACL 2021

• Evidence-based Verification for Real World Information Needs
  

  James Thorne, Max Glockner, Gisela Vallejo, Andreas Vlachos, Iryna Gurevych
  arxiv preprint.
  Code

• KILT:a Benchmark for Knowledge Intensive Language Tasks
  

  Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vassilis Plachouras, Tim Rocktäschel, Sebastian Riedel
  NAACL 2021
  Code
  Website

• From Natural Language Processing to Neural Databases
  

  James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy
  Proceedings of the VLDB Endowment. Volume 14

• Elastic weight consolidation for better bias inoculation
  

  James Thorne, Andreas Vlachos
  European Chapter of the Association for Computational Linguistics (EACL) 2021
  Code
  Slides Poster

2020

• Neural Database Operator Model
  

  James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy
  West Coast NLP Summit 2020 (WecNLP)

• Neural Databases
  

  James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy
  arxiv preprint

2019

• The FEVER2.0 Shared Task
  

  James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
  Proceedings of the FEVER2019 workshop at EMNLP 2019

• Evaluating adversarial attacks against multiple fact verification systems
  

  James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
  EMNLP 2019

• Generating Token-Level Explanations for Natural Language Inference
  

  James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
  NAACL 2019

• Adversarial Attacks against Fact Extraction and VERification
  

  James Thorne, Andreas Vlachos
  Arxiv Preprint

2018

• The Fact Extraction and VERification Shared Task
  

  James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
  Proceedings of the FEVER workshop at EMNLP 2018

• Automated Fact Checking: Task formulations, methods and future directions
  

  James Thorne, Andreas Vlachos
  COLING 2018

• FEVER: a large-scale dataset for Fact Extraction and VERificiation
  

  James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal
  NAACL 2018
  Code
  Data

• Bridging the Gaps: Multi-Task Learning for Domain Transfer of Hate Speech Detection
  

  Zeerak Waseem, James Thorne, Joachim Bingel
  Springer (Online Harassment)
  Code

2017

• Fake News Stance Detection using Stacked Ensemble of Classifiers
  

  James Thorne, Mingjie Chen, Giorgos Myrianthous, Jiashu Pu, Xiaoxuan Wang, Andreas Vlachos
  Natural Language Processing meets Journalism workshop at EMNLP 2017
  Code

• An Extensible Framework for Verification of Numerical Claims
  

  James Thorne and Andreas Vlachos
  European Chapter of the Association for Computational Linguistics (EACL) 2017
  Code

Thesis

• Evidence-based verification and correction of textual claims
  

  James Thorne
  University of Cambridge