Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation

2024/02/20 by Himmi, Anas, Staerman, Guillaume, Picot, Marine +2 · 4 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2402.13331

Abstract

Hallucinated translations pose significant threats and safety concerns when it comes to the practical deployment of machine translation systems. Previous research works have identified that detectors exhibit complementary performance different detectors excel at detecting different types of hallucinations. In this paper, we propose to address the limitations of individual detectors by combining them and introducing a straightforward method for aggregating multiple detectors. Our results demonstrate the efficacy of our aggregated detector, providing a promising step towards evermore reliable machine translation systems.

Cited by

• M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
• Training-free Truthfulness Detection via Sparse MLP Value Vectors
• MMD-Flagger: Leveraging Maximum Mean Discrepancy to Detect Hallucinations
• Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement

Related

• Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation
• Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation
• Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
• Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
• Probing Causes of Hallucinations in Neural Machine Translations