Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. In this work, we first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinated vs. non-hallucinated outputs generated via source perturbations. We then show that these symptoms are reliable indicators of natural hallucinations, by using them to design a lightweight hallucination detector which outperforms both model-free baselines and strong classifiers based on quality estimation or large pre-trained models on manually annotated English-Chinese and German-English translation test beds.
Code (1)
Tasks
HallucinationMachine TranslationTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
While the problem of hallucinations in neural machine translation has long been recognized, so far the progress on its alleviation is very little. Indeed, recently it turned out that without artificially encouraging mode…
Machine TranslationSentenceSentence SimilarityTranslationHallucinations in Large Multilingual Translation Models
Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications. However, when de…
Language ModelingLanguage ModellingLarge Language ModelMachine Translation+1Reducing Hallucinations in Neural Machine Translation with Feature Attribution
Neural conditional language generation models achieve the state-of-the-art in Neural Machine Translation (NMT) but are highly dependent on the quality of parallel training dataset. When trained on low-quality datasets, t…
Machine TranslationNMTText GenerationTranslationEnhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation
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 complementar…
HallucinationMachine TranslationTranslationMachine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models
Recent advancements in massively multilingual machine translation systems have significantly enhanced translation accuracy; however, even the best performing systems still generate hallucinations, severely impacting user…
HallucinationMachine TranslationSemantic SimilaritySemantic Textual Similarity+2