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

Team Trifecta at Factify5WQA: Setting the Standard in Fact Verification with Fine-Tuning (2403.10281v1)

Published 15 Mar 2024 in cs.CL, cs.AI, and cs.LG

Abstract: In this paper, we present Pre-CoFactv3, a comprehensive framework comprised of Question Answering and Text Classification components for fact verification. Leveraging In-Context Learning, Fine-tuned LLMs, and the FakeNet model, we address the challenges of fact verification. Our experiments explore diverse approaches, comparing different Pre-trained LLMs, introducing FakeNet, and implementing various ensemble methods. Notably, our team, Trifecta, secured first place in the AAAI-24 Factify 3.0 Workshop, surpassing the baseline accuracy by 103% and maintaining a 70% lead over the second competitor. This success underscores the efficacy of our approach and its potential contributions to advancing fact verification research.

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 (24)
  1. Team triple-check at factify 2: Parameter-efficient large foundation models with feature representations for multi-modal fact verification, arXiv preprint arXiv:2302.07740 (2023).
  2. Factify 2: A multimodal fake news and satire news dataset, in: Proceedings of DeFactify 2: Second Workshop on Multimodal Fact-Checking and Hate Speech Detection, CEUR, 2023.
  3. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing, arXiv preprint arXiv:2111.09543 (2021).
  4. Information credibility on twitter, in: Proceedings of the 20th international conference on World wide web, 2011, pp. 675–684.
  5. Enquiring minds: Early detection of rumors in social media from enquiry posts, in: Proceedings of the 24th international conference on world wide web, 2015, pp. 1395–1405.
  6. Fndnet–a deep convolutional neural network for fake news detection, Cognitive Systems Research 61 (2020) 32–44.
  7. Fake news detection using bi-directional lstm-recurrent neural network, Procedia Computer Science 165 (2019) 74–82.
  8. Eann: Event adversarial neural networks for multi-modal fake news detection, in: Proceedings of the 24th acm sigkdd international conference on knowledge discovery & data mining, 2018, pp. 849–857.
  9. Multimodal fusion with co-attention networks for fake news detection, in: Findings of the association for computational linguistics: ACL-IJCNLP 2021, 2021, pp. 2560–2569.
  10. Overview of factify5wqa: Fact verification through 5w question-answering, in: proceedings of DeFactify 3.0: third workshop on Multimodal Fact-Checking and Hate Speech Detection, CEUR, 2024.
  11. Attention is all you need, Advances in neural information processing systems 30 (2017).
  12. Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv:1810.04805 (2018).
  13. Language models are few-shot learners, Advances in neural information processing systems 33 (2020) 1877–1901.
  14. SQuAD: 100,000+ Questions for Machine Comprehension of Text, arXiv e-prints (2016) arXiv:1606.05250. arXiv:1606.05250.
  15. Logically at factify 2022: Multimodal fact verification, arXiv preprint arXiv:2112.09253 (2021).
  16. Ino at factify 2: Structure coherence based multi-modal fact verification, arXiv preprint arXiv:2303.01510 (2023).
  17. FACTIFY-5WQA: 5W aspect-based fact verification through question answering, in: A. Rogers, J. Boyd-Graber, N. Okazaki (Eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Toronto, Canada, 2023, pp. 10421–10440. URL: https://aclanthology.org/2023.acl-long.581. doi:10.18653/v1/2023.acl-long.581.
  18. Bleu: a method for automatic evaluation of machine translation, in: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, 2002, pp. 311–318.
  19. Roberta: A robustly optimized bert pretraining approach, arXiv preprint arXiv:1907.11692 (2019).
  20. Language models are unsupervised multitask learners, OpenAI blog 1 (2019) 9.
  21. Exploring the limits of transfer learning with a unified text-to-text transformer, The Journal of Machine Learning Research 21 (2020) 5485–5551.
  22. Deberta: Decoding-enhanced bert with disentangled attention, arXiv preprint arXiv:2006.03654 (2020).
  23. Chain-of-thought prompting elicits reasoning in large language models, in: S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh (Eds.), Advances in Neural Information Processing Systems, volume 35, Curran Associates, Inc., 2022, pp. 24824–24837. URL: https://proceedings.neurips.cc/paper_files/paper/2022/file/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf.
  24. Llama 2: Open foundation and fine-tuned chat models, arXiv preprint arXiv:2307.09288 (2023).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Shang-Hsuan Chiang (4 papers)
  2. Ming-Chih Lo (4 papers)
  3. Lin-Wei Chao (2 papers)
  4. Wen-Chih Peng (47 papers)
Citations (2)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets