# Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization

arXiv: https://arxiv.org/abs/2501.17295 · HTML: https://mlsanity.com/paper/2501.17295/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 28 of 28)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics](https://mlsanity.com/paper/2111.09388/) (2021)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better](https://mlsanity.com/paper/2212.08597/) (2022)
- [Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation](https://mlsanity.com/paper/2010.10907/) (2020)
- [Measuring the Mixing of Contextual Information in the Transformer](https://mlsanity.com/paper/2203.04212/) (2022)
- [Contrastive Search Is What You Need For Neural Text Generation](https://mlsanity.com/paper/2210.14140/) (2022)
- [Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation](https://mlsanity.com/paper/2305.09860/) (2023)
- [Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer](https://mlsanity.com/paper/2205.11631/) (2022)
- [Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://mlsanity.com/paper/2309.07098/) (2023)
- [HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation](https://mlsanity.com/paper/2305.11746/) (2023)
- [Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Task](https://mlsanity.com/paper/1907.06488/) (2019)
- [SALTED: A Framework for SAlient Long-Tail Translation Error Detection](https://mlsanity.com/paper/2205.09988/) (2022)
- [BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric](https://mlsanity.com/paper/2212.08486/) (2022)

## Built on by (most cited first, 6 of 6)

- [Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation](https://mlsanity.com/paper/2503.19622/) (2025)
- [The Illusionist's Prompt: Exposing the Factual Vulnerabilities of Large Language Models with Linguistic Nuances](https://mlsanity.com/paper/2504.02865/) (2025)
- [Leveraging NTPs for Efficient Hallucination Detection in VLMs](https://mlsanity.com/paper/2509.20379/) (2025)
- [STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation](https://mlsanity.com/paper/2608.27161/) (2026)
- [RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation](https://mlsanity.com/paper/2507.22219/) (2025)
- [Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement](https://mlsanity.com/paper/2602.09486/) (2026)

## Abstract (arXiv)

Machine Translation (MT) is undergoing a paradigm shift, with systems based on fine-tuned large language models (LLM) becoming increasingly competitive with traditional encoder-decoder models trained specifically for translation tasks. However, LLM-based systems are at a higher risk of generating hallucinations, which can severely undermine user's trust and safety. Most prior research on hallucination mitigation focuses on traditional MT models, with solutions that involve post-hoc mitigation - detecting hallucinated translations and re-translating them. While effective, this approach introduces additional complexity in deploying extra tools in production and also increases latency. To address these limitations, we propose a method that intrinsically learns to mitigate hallucinations during the model training phase. Specifically, we introduce a data creation framework to generate hallucination focused preference datasets. Fine-tuning LLMs on these preference datasets reduces the hallucination rate by an average of 96% across five language pairs, while preserving overall translation quality. In a zero-shot setting our approach reduces hallucinations by 89% on an average across three unseen target languages.