Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables (2402.13028v1)

Published 20 Feb 2024 in cs.CL and cs.AI

Abstract: Fact checking aims to predict claim veracity by reasoning over multiple evidence pieces. It usually involves evidence retrieval and veracity reasoning. In this paper, we focus on the latter, reasoning over unstructured text and structured table information. Previous works have primarily relied on fine-tuning pretrained LLMs or training homogeneous-graph-based models. Despite their effectiveness, we argue that they fail to explore the rich semantic information underlying the evidence with different structures. To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC. Our approach leverages a heterogeneous evidence graph, with words as nodes and thoughtfully designed edges representing different evidence properties. We perform information propagation via a relational graph neural network, facilitating interactions between claims and evidence. An attention-based method is utilized to integrate information, combined with a LLM for generating predictions. We introduce a multitask loss function to account for potential inaccuracies in evidence retrieval. Comprehensive experiments on the large fact checking dataset FEVEROUS demonstrate the effectiveness of HeterFC. Code will be released at: https://github.com/Deno-V/HeterFC.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
  2. FaBULOUS: Fact-checking Based on Understanding of Language Over Unstructured and Structured information. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 31–39. Association for Computational Linguistics.
  3. Reading Wikipedia to Answer Open-Domain Questions. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1870–1879. Association for Computational Linguistics.
  4. EvidenceNet: Evidence Fusion Network for Fact Verification. In Proceedings of the ACM Web Conference 2022, 2636–2645.
  5. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019, 2478–2486. ACM.
  6. Funkquist, M. 2021. Combining sentence and table evidence to predict veracity of factual claims using TaPaS and RoBERTa. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 92–100. Association for Computational Linguistics.
  7. Verdict Inference with Claim and Retrieved Elements Using RoBERTa. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 60–65. Association for Computational Linguistics.
  8. Dual-Channel Evidence Fusion for Fact Verification over Texts and Tables. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 5232–5242. Association for Computational Linguistics.
  9. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  10. Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verification. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 21–30. Association for Computational Linguistics.
  11. Fact-checking as risk communication: the multi-layered risk of misinformation in times of COVID-19. Journal of Risk Research, 23: 1052 – 1059.
  12. Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing. arXiv preprint arXiv:2304.12888.
  13. Roberta: A robustly optimized bert pretraining approach. ArXiv preprint, abs/1907.11692.
  14. Fine-grained Fact Verification with Kernel Graph Attention Network. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 7342–7351. Association for Computational Linguistics.
  15. Malon, C. 2021. Team Papelo at FEVEROUS: Multi-hop Evidence Pursuit. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 40–49. Association for Computational Linguistics.
  16. Distributed Representations of Words and Phrases and their Compositionality. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, 3111–3119.
  17. The Covid‐19 ‘infodemic’: a new front for information professionals. Health Information and Libraries Journal, 37: 233 – 239.
  18. Modeling relational data with graph convolutional networks. In European semantic web conference, 593–607. Springer.
  19. Bert for evidence retrieval and claim verification. In European Conference on Information Retrieval, 359–366.
  20. Open domain question answering using early fusion of knowledge bases and text. arXiv preprint arXiv:1809.00782.
  21. FEVER: a Large-scale Dataset for Fact Extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 809–819. Association for Computational Linguistics.
  22. Fact or Fiction: Verifying Scientific Claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 7534–7550. Association for Computational Linguistics.
  23. Wang, W. Y. 2017. “Liar, Liar Pants on Fire”: A New Benchmark Dataset for Fake News Detection. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 422–426. Association for Computational Linguistics.
  24. Generating Scientific Claims for Zero-Shot Scientific Fact Checking. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2448–2460. Association for Computational Linguistics.
  25. Adversarial contrastive learning for evidence-aware fake news detection with graph neural networks. arXiv preprint arXiv:2210.05498.
  26. Counterfactual Debiasing for Fact Verification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 6777–6789.
  27. Evidence-aware Fake News Detection with Graph Neural Networks. Proceedings of the ACM Web Conference 2022.
  28. Relation-aware Heterogeneous Graph for User Profiling. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 3573–3577.
  29. Hierarchical Graph Representation Learning with Differentiable Pooling. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, 4805–4815.
  30. Heterogeneous Graph Learning for Visual Commonsense Reasoning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, 2765–2775.
  31. Defending Against Neural Fake News. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, 9051–9062.
  32. Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  33. Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada, August 13 - 17, 2017, 635–644. ACM.
  34. Reasoning Over Semantic-Level Graph for Fact Checking. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 6170–6180. Association for Computational Linguistics.
  35. GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 892–901. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Haisong Gong (8 papers)
  2. Weizhi Xu (13 papers)
  3. Qiang Liu (405 papers)
  4. Liang Wang (512 papers)
  5. Shu Wu (109 papers)
Citations (2)
View on Semantic Scholar