Less defined knowledge and more true alarms: Reference-based phishing detection without a pre-defined reference list

R Liu, Y Lin, X Teoh, G Liu, Z Huang… - 33rd USENIX Security …, 2024 - usenix.org
Phishing, a pervasive form of social engineering attack that compromises user credentials,
has led to significant financial losses and undermined public trust. Modern phishing …

Atomic Inference for NLI with Generated Facts as Atoms

J Stacey, P Minervini, H Dubossarsky… - Proceedings of the …, 2024 - aclanthology.org
With recent advances, neural models can achieve human-level performance on various
natural language tasks. However, there are no guarantees that any explanations from these …

EXCGEC: A Benchmark of Edit-wise Explainable Chinese Grammatical Error Correction

J Ye, S Qin, Y Li, X Cheng, L Qin, HT Zheng… - arxiv preprint arxiv …, 2024 - arxiv.org
Existing studies explore the explainability of Grammatical Error Correction (GEC) in a limited
scenario, where they ignore the interaction between corrections and explanations. To bridge …

Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4

AP Gema, G Hong, P Minervini, L Daines… - arxiv preprint arxiv …, 2024 - arxiv.org
The NLI4CT task assesses Natural Language Inference systems in predicting whether
hypotheses entail or contradict evidence from Clinical Trial Reports. In this study, we …

Enhancing adversarial robustness in Natural Language Inference using explanations

A Koulakos, M Lymperaiou, G Filandrianos… - arxiv preprint arxiv …, 2024 - arxiv.org
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits
of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the …

Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints

AP Gema, C Lee, P Minervini, L Daines… - arxiv preprint arxiv …, 2024 - arxiv.org
The MEDIQA-CORR 2024 shared task aims to assess the ability of Large Language Models
(LLMs) to identify and correct medical errors in clinical notes. In this study, we evaluate the …

Enhancing In-Context Learning with Semantic Representations for Relation Extraction

P Han, LK Pereira, F Cheng, WJ She… - arxiv preprint arxiv …, 2024 - arxiv.org
In this work, we employ two AMR-enhanced semantic representations for ICL on RE: one
that explores the AMR structure generated for a sentence at the subgraph level (shortest …