Zan Hongying, Arifa Javed, Muhammad Abdullah, Javed Rashid, Muhammad Faheem
{"title":"Large Language Models With Contrastive Decoding Algorithm for Hallucination Mitigation in Low-Resource Languages","authors":"Zan Hongying, Arifa Javed, Muhammad Abdullah, Javed Rashid, Muhammad Faheem","doi":"10.1049/cit2.70004","DOIUrl":null,"url":null,"abstract":"<p>Neural machine translation (NMT) has advanced with deep learning and large-scale multilingual models, yet translating low-resource languages often lacks sufficient training data and leads to hallucinations. This often results in translated content that diverges significantly from the source text. This research proposes a refined Contrastive Decoding (CD) algorithm that dynamically adjusts weights of log probabilities from strong expert and weak amateur models to mitigate hallucinations in low-resource NMT and improve translation quality. Advanced large language NMT models, including ChatGLM and LLaMA, are fine-tuned and implemented for their superior contextual understanding and cross-lingual capabilities. The refined CD algorithm evaluates multiple candidate translations using BLEU score, semantic similarity, and Named Entity Recognition accuracy. Extensive experimental results show substantial improvements in translation quality and a significant reduction in hallucination rates. Fine-tuned models achieve higher evaluation metrics compared to baseline models and state-of-the-art models. An ablation study confirms the contributions of each methodological component and highlights the effectiveness of the refined CD algorithm and advanced models in mitigating hallucinations. Notably, the refined methodology increased the BLEU score by approximately 30% compared to baseline models.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"10 4","pages":"1104-1117"},"PeriodicalIF":7.3000,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.70004","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cit2.70004","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Neural machine translation (NMT) has advanced with deep learning and large-scale multilingual models, yet translating low-resource languages often lacks sufficient training data and leads to hallucinations. This often results in translated content that diverges significantly from the source text. This research proposes a refined Contrastive Decoding (CD) algorithm that dynamically adjusts weights of log probabilities from strong expert and weak amateur models to mitigate hallucinations in low-resource NMT and improve translation quality. Advanced large language NMT models, including ChatGLM and LLaMA, are fine-tuned and implemented for their superior contextual understanding and cross-lingual capabilities. The refined CD algorithm evaluates multiple candidate translations using BLEU score, semantic similarity, and Named Entity Recognition accuracy. Extensive experimental results show substantial improvements in translation quality and a significant reduction in hallucination rates. Fine-tuned models achieve higher evaluation metrics compared to baseline models and state-of-the-art models. An ablation study confirms the contributions of each methodological component and highlights the effectiveness of the refined CD algorithm and advanced models in mitigating hallucinations. Notably, the refined methodology increased the BLEU score by approximately 30% compared to baseline models.
期刊介绍:
CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.