Papers by John Dougrez-Lewis
Assessing the Reasoning Capabilities of LLMs in the context of Evidence-based Claim Verification (2025.findings-acl)
Copied to clipboard
John Dougrez-Lewis, Mahmud Elahi Akhter, Federico Ruggeri, Sebastian Löbbers, Yulan He, Maria Liakata
| Challenge: | Large Language Models (LLMs) have shown remarkable proficiency in complex tasks where reasoning capabilities are paramount. |
| Approach: | They propose a framework to break down claims into atomic reasoning types needed for verification. |
| Outcome: | The proposed framework breaks down claims into atomic reasoning types needed for verification. |
Knowledge Graphs for Real-World Rumour Verification (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in automated rumour verification have limited results in real-world scenarios. |
| Approach: | They propose to use Twitter responses to construct knowledge graphs based on the PHEME dataset to identify discrepancies between the evidence retrieved and PHE ME’s labels. |
| Outcome: | The proposed model outperforms the state-of-the-art on PHEME and has superior generisability when evaluated on a temporally distant rumour verification dataset. |
Learning Disentangled Latent Topics for Twitter Rumour Veracity Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to rumour veracity classification relied on feature engineering. |
| Approach: | They propose a model which disentangles the informational content of a tweet from the manner in which it is written. |
| Outcome: | The proposed model disentangles the informational content of a tweet from the manner in which the information is written. |