Abstract
Fact verification systems assess a claim’s veracity based on evidence. An important consideration in designing them is faithfulness, i.e. generating explanations that accurately reflect the reasoning of the model. Recent works have focused on natural logic, which operates directly on natural language by capturing the semantic relation of spans between an aligned claim with its evidence via set-theoretic operators. However, these approaches rely on substantial resources for training, which are only available for high-resource languages. To this end, we propose to use question answering to predict natural logic operators, taking advantage of the generalization capabilities of instruction-tuned language models. Thus, we obviate the need for annotated training data while still relying on a deterministic inference system. In a few-shot setting on FEVER, our approach outperforms the best baseline by 4.3 accuracy points, including a state-of-the-art pre-trained seq2seq natural logic system, as well as a state-of-the-art prompt-based classifier. Our system demonstrates its robustness and portability, achieving competitive performance on a counterfactual dataset and surpassing all approaches without further annotation on a Danish verification dataset. A human evaluation indicates that our approach produces more plausible proofs with fewer erroneous natural logic operators than previous natural logic-based systems.- Anthology ID:
- 2023.emnlp-main.521
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8376–8391
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.521
- DOI:
- 10.18653/v1/2023.emnlp-main.521
- Cite (ACL):
- Rami Aly, Marek Strong, and Andreas Vlachos. 2023. QA-NatVer: Question Answering for Natural Logic-based Fact Verification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8376–8391, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- QA-NatVer: Question Answering for Natural Logic-based Fact Verification (Aly et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.521.pdf