# Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection

arXiv: https://arxiv.org/abs/2301.07779 · HTML: https://mlsanity.com/paper/2301.07779/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 75 references that are in the map.
- First posted on arXiv 18 Jan 2023.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](https://mlsanity.com/paper/1907.05791/) (2019)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context](https://mlsanity.com/paper/1805.04623/) (2018)
- [On Adversarial Examples for Character-Level Neural Machine Translation](https://mlsanity.com/paper/1806.09030/) (2018)
- [Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation](https://mlsanity.com/paper/2010.10907/) (2020)
- [The FLoRes Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English](https://mlsanity.com/paper/1902.01382/) (2019)
- [On the Inference Calibration of Neural Machine Translation](https://mlsanity.com/paper/2005.00963/) (2020)
- [Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2208.05309/) (2022)
- [TransQuest: Translation Quality Estimation with Cross-lingual Transformers](https://mlsanity.com/paper/2011.01536/) (2020)
- [A causal framework for explaining the predictions of black-box sequence-to-sequence models](https://mlsanity.com/paper/1707.01943/) (2017)
- [Unbabel's Participation in the WMT20 Metrics Shared Task](https://mlsanity.com/paper/2010.15535/) (2020)

## Built on by (most cited first, 30 of 44)

- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [LM-Polygraph: Uncertainty Estimation for Language Models](https://mlsanity.com/paper/2311.07383/) (2023)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness](https://mlsanity.com/paper/2411.03350/) (2024)
- [Calibrated Language Models Must Hallucinate](https://mlsanity.com/paper/2311.14648/) (2023)
- [Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph](https://mlsanity.com/paper/2406.15627/) (2024)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [Unfamiliar Finetuning Examples Control How Language Models Hallucinate](https://mlsanity.com/paper/2403.05612/) (2024)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation](https://mlsanity.com/paper/2305.11746/) (2023)
- [Generative AI for Synthetic Data Generation: Methods, Challenges and the Future](https://mlsanity.com/paper/2403.04190/) (2024)
- [Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework](https://mlsanity.com/paper/2406.03075/) (2024)
- [Comparing Hallucination Detection Metrics for Multilingual Generation](https://mlsanity.com/paper/2402.10496/) (2024)
- [An Empirical Study of Translation Hypothesis Ensembling with Large Language Models](https://mlsanity.com/paper/2310.11430/) (2023)
- [Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization](https://mlsanity.com/paper/2311.09335/) (2023)
- [Teaching LLMs to Abstain across Languages via Multilingual Feedback](https://mlsanity.com/paper/2406.15948/) (2024)
- [Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models](https://mlsanity.com/paper/2407.16470/) (2024)
- [DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models](https://mlsanity.com/paper/2411.18659/) (2024)
- [Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations](https://mlsanity.com/paper/2402.11770/) (2024)
- [Hallucination Detection for Grounded Instruction Generation](https://mlsanity.com/paper/2310.15319/) (2023)
- [Low-resource neural machine translation with morphological modeling](https://mlsanity.com/paper/2404.02392/) (2024)
- [QE4PE: Word-level Quality Estimation for Human Post-Editing](https://mlsanity.com/paper/2503.03044/) (2025)
- [Neural Message-Passing on Attention Graphs for Hallucination Detection](https://mlsanity.com/paper/2509.24770/) (2025)
- [A Unified Definition of Hallucination: It's The World Model, Stupid!](https://mlsanity.com/paper/2512.21577/) (2025)
- [Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation](https://mlsanity.com/paper/2311.09467/) (2023)
- [Controlling Large Language Model with Latent Actions](https://mlsanity.com/paper/2503.21383/) (2025)

## Abstract (arXiv)

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.