Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust. |
| Approach: | They propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model. |
| Outcome: | The proposed detector outperforms existing models and is competitive with detectors that employ external models trained on millions of samples. |
Similar Papers
Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is becoming more accurate, but hallucinations are extremely pathological . previous work focused on artificial settings where the problem is amplified, disregarding some common types of hallucines . |
| Approach: | They propose a method for alleviating hallucinations at test time that significantly reduces the hallucinic rate. |
| Outcome: | The proposed method significantly reduces the hallucinatory rate in a natural setting. |
Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better (2023.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that without artificially encouraging models to hallucinate, existing methods fall short . hallucinations are cases when the model generates output that is partially or fully unrelated to the source sentence. |
| Approach: | They propose a method that evaluates the percentage of the source contribution to a generated translation. |
| Outcome: | The proposed method improves detection accuracy for the most severe hallucinations by a factor of 2. |
Contrastive Decoding Reduces Hallucinations in Large Multilingual Machine Translation Models (2024.eacl-long)
Copied to clipboard
| Challenge: | Hallucinations occur when the target side sentence is detached from the source side sentence, or in other words, when there is a low contribution of the source sentence to the generation of the target sentence. |
| Approach: | They propose to use Contrastive Decoding to maximise the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs. |
| Outcome: | The proposed algorithm maximises the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs. |
The Curious Case of Hallucinations in Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) suffers from well known pathologies such as coverage, mistranslation of named entities, etc. |
| Approach: | They propose a theory that explains hallucinations under source perturbation and a method that generates hallucines under corpus-level noise without any source perturbations. |
| Outcome: | The proposed hypothesis is validated by a corpus-level noise analysis and is validateable in other datasets. |
OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations and omissions in Machine Translation systems focus on analyzing the model’s internal states or relying on external tools. |
| Approach: | They propose an Optimal Transport-based word aligner specifically designed to enhance the detection of hallucinations and omissions in Machine Translation systems. |
| Outcome: | The proposed method is competitive with state-of-the-art methods across 18 language pairs on the HalOmi benchmark and shows promising features. |
Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) systems suffer from various pathologies, including the generation of translations that are detached from the source content, typically known as hallucinations. |
| Approach: | They propose to combine detectors and introduce a method for aggregating detectors to detect hallucinations. |
| Outcome: | The proposed method provides a promising step towards evermore reliable machine translation systems. |
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation suffers from exposure bias, and alternative approaches to mitigate this are under debate. |
| Approach: | They propose to reduce exposure bias by using minimum risk training to mitigate hallucinations . they find that exposure bias is more problematic under domain shift . |
| Outcome: | The proposed methods can reduce exposure bias even on in-domain test sets. |
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection (2023.tacl-1)
Copied to clipboard
| Challenge: | Neural sequence generation models produce outputs that are unrelated to the source text, and are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate their impact. |
| Approach: | They first identify internal model symptoms of hallucinations by analyzing the relative token contributions to the generation in contrastive hallucinous vs. non-hallucinated outputs generated via source perturbations. |
| Outcome: | The proposed detector outperforms both baseline models and strong classifiers on English-Chinese and German-English translation test beds. |
HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation (2023.emnlp-main)
Copied to clipboard
David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Loic Barrault, Marta Costa-jussà
| Challenge: | Previously available quality assessments do not distinguish between hallucinations and omissions. |
| Approach: | They propose to annotate hallucinations and omissions in machine translation using a single language pair. |
| Outcome: | The proposed dataset covers 18 translation directions with varying resource levels and scripts. |
Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Decode-Only models propagate information from left to right, but the model's attention still focuses on the visual representations, resulting in hallucinations. |
| Approach: | They propose to leverage the core information embedded in semantic representations to enhance the model's visual understanding by leveraging the attention distributions. |
| Outcome: | The proposed method reduces hallucinations by 80% by aligning the attention distribution with the actual information flow. |