Qa-natver: Question answering for natural logic-based fact verification

R Aly, M Strong, A Vlachos - arxiv preprint arxiv:2310.14198, 2023 - arxiv.org
Fact verification systems assess a claim's veracity based on evidence. An important
consideration in designing them is faithfulness, ie generating explanations that accurately …

Zero-Shot Fact Verification via Natural Logic and Large Language Models

M Strong, R Aly, A Vlachos - arxiv preprint arxiv:2410.03341, 2024 - arxiv.org
The recent development of fact verification systems with natural logic has enhanced their
explainability by aligning claims with evidence through set-theoretic operators, providing …

InfoLossQA: Characterizing and recovering information loss in text simplification

J Trienes, S Joseph, J Schlötterer, C Seifert… - arxiv preprint arxiv …, 2024 - arxiv.org
Text simplification aims to make technical texts more accessible to laypeople but often
results in deletion of information and vagueness. This work proposes InfoLossQA, a …

Rapper: Reinforced rationale-prompted paradigm for natural language explanation in visual question answering

KP Chang, CP Huang, WY Cheng, FE Yang… - The Twelfth …, 2024 - openreview.net
Natural Language Explanation (NLE) in vision and language tasks aims to provide human-
understandable explanations for the associated decision-making process. In practice, one …

uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization

A Nagar, Y Liu, AT Liu, V Schlegel, VP Dwivedi… - arxiv preprint arxiv …, 2024 - arxiv.org
Medical abstractive summarization faces the challenge of balancing faithfulness and
informativeness. Current methods often sacrifice key information for faithfulness or introduce …

Distilling Robustness into Natural Language Inference Models with Domain-Targeted Augmentation

J Stacey, M Rei - arxiv preprint arxiv:2305.13067, 2023 - arxiv.org
Knowledge distillation optimises a smaller student model to behave similarly to a larger
teacher model, retaining some of the performance benefits. While this method can improve …

A hypothesis-driven framework for the analysis of self-rationalising models

M Braun, J Kunz - arxiv preprint arxiv:2402.04787, 2024 - arxiv.org
The self-rationalising capabilities of LLMs are appealing because the generated
explanations can give insights into the plausibility of the predictions. However, how faithful …

DECT: Harnessing LLM-assisted Fine-Grained Linguistic Knowledge and Label-Switched and Label-Preserved Data Generation for Diagnosis of Alzheimer's Disease

T Mo, JCK Lam, VOK Li, LYL Cheung - arxiv preprint arxiv:2502.04394, 2025 - arxiv.org
Alzheimer's Disease (AD) is an irreversible neurodegenerative disease affecting 50 million
people worldwide. Low-cost, accurate identification of key markers of AD is crucial for timely …