paper-with-me

Papers

Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection

2023-01-18 · Weijia Xu, Sweta Agrawal, Eleftheria Briakou, Marianna J. Martindale, Marine Carpuat

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.

📄 PDF Abstract BibTeX arXiv:2301.07779

Code (1)

weijia-xu/hallucinations-in-nmt 공식 구현 tf

Tasks

HallucinationMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better

2022-12-16 · David Dale, Elena Voita, Loïc Barrault, Marta R. Costa-jussà

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 SimilarityTranslation

Hallucinations in Large Multilingual Translation Models

2023-03-28 · Nuno M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow 외

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+1

Reducing Hallucinations in Neural Machine Translation with Feature Attribution

2022-11-17 · Joël Tang, Marina Fomicheva, Lucia Specia

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 GenerationTranslation

Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation

2024-02-20 · Anas Himmi, Guillaume Staerman, Marine Picot, Pierre Colombo 외

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 TranslationTranslation

Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models

2024-07-23 · Kenza Benkirane, Laura Gongas, Shahar Pelles, Naomi Fuchs 외

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