Augmenting Text to Increase Translation Difficulty

• URL: http://arxiv.org/abs/2608.15932v1
• Date: Sun, 16 Aug 2026 21:13:21 GMT
• Title: Augmenting Text to Increase Translation Difficulty
• Abstract summary: Adversarial Translation Optimization (ATO) uses gradients from a combined difficulty and fluency objective to iteratively replace tokens.<n>Our ATO-modified benchmark lowers average translation quality (xCOMET) from 0.93 to 0.82, compared to 0.88 for paraphrasing and 0.86 for a zero-shot baseline.<n>Human evaluation shows the modified texts are somewhat less natural than the baselines but remain reasonably grammatical and plausible.
• Score: 10.250408287553373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As state-of-the-art machine translation models saturate standard benchmarks, the field needs more challenging evaluations to distinguish between models of varying quality. We propose augmenting existing benchmarks to increase translation difficulty by combining adversarial optimization with a differentiable translation difficulty estimator. Our Adversarial Translation Optimization (ATO) uses gradients from a combined difficulty and fluency objective to iteratively replace tokens. Because each step branches over candidate substitutions at every position, optimization becomes a tree search problem, which we address with Beam Search. ATO offers a gradient-based alternative to LLM-based dataset creation without LLM prompting, expensive human curation, or task-specific model training. Our ATO-modified benchmark lowers average translation quality (xCOMET) from 0.93 to 0.82, compared to 0.88 for paraphrasing and 0.86 for a zero-shot baseline. Human evaluation shows the modified texts are somewhat less natural than the baselines but remain reasonably grammatical and plausible while being substantially harder to translate. We release two datasets of 350 English texts each, generated by our methods, as well as the code.

Related papers

• Generating Adversarial Texts for Machine Translation via GRPO [9.016860740260679]
  We propose a scalable reinforcement-learning-based approach for rewriting existing source texts.<n>On WMT25, our approach substantially reduces average COMET translation quality from 0.63 to 0.48, while preserving grammaticality and readability.<n> Evaluations on the unseen WMT19-WMT24 benchmarks confirm that this behavior generalizes beyond the training data.
  arXiv  Detail & Related papers  (2026-09-05T12:06:59Z)
• Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech [50.45710815530982]
  Simultaneous speech translation (SST) generates translations while receiving partial speech input.<n>Recent advances show that large language models (LLMs) can substantially improve SST quality, but at the cost of high computational overhead.<n>We propose a Hierarchical Policy Optimization (HPO) approach that trains post-train models on imperfect SFT data.<n> Experiments on English to Chinese/German/Japanese demonstrate improvements of over +7 COMET score and +1.25 MetricX score at a latency of 1.5 seconds.
  arXiv  Detail & Related papers  (2026-04-22T19:43:51Z)
• Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets [2.0199251985015434]
  We present a fully automated framework designed to enable scalable, high-quality translation of datasets and benchmarks.<n>We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages.
  arXiv  Detail & Related papers  (2026-02-25T18:58:25Z)
• COMET-poly: Machine Translation Metric Grounded in Other Candidates [63.82506348745169]
  We propose two automated metrics that incorporate additional information beyond the single translation.<n> COMET-polycand uses alternative translations of the same source sentence to compare and contrast with the translation at hand.<n>We find that including a single additional translation in COMET-polycand improves the segment-level metric performance.
  arXiv  Detail & Related papers  (2025-08-25T22:55:22Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)
• Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages [0.34998703934432673]
  We build a single-decoder neural machine translation system for Dravidian-Dravidian multilingual translation. Our model achieves scores within 3 BLEU of large-scale pivot-based models when it is trained on 50% of the language directions.
  arXiv  Detail & Related papers  (2023-08-10T13:38:09Z)
• MTUncertainty: Assessing the Need for Post-editing of Machine Translation Outputs by Fine-tuning OpenAI LLMs [6.822926897514793]
  TQE is critical in assessing both machine translation (MT) and human translation (HT) quality without reference translations. This work examines whether the state-of-the-art large language models (LLMs) can be used for this purpose. We take OpenAI models as the best state-of-the-art technology and approach TQE as a binary classification task.
  arXiv  Detail & Related papers  (2023-07-31T21:13:30Z)
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation [53.55009917938002]
  We propose to refine the mined bitexts via automatic editing. Experiments demonstrate that our approach successfully improves the quality of CCMatrix mined bitext for 5 low-resource language-pairs and 10 translation directions by up to 8 BLEU points.
  arXiv  Detail & Related papers  (2021-11-12T16:00:39Z)
• Improving Multilingual Translation by Representation and Gradient Regularization [82.42760103045083]
  We propose a joint approach to regularize NMT models at both representation-level and gradient-level. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance.
  arXiv  Detail & Related papers  (2021-09-10T10:52:21Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)
• Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation [98.11249019844281]
  Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. We propose reverse KD to rejuvenate more alignments for low-frequency target words. Results demonstrate that the proposed approach can significantly and universally improve translation quality.
  arXiv  Detail & Related papers  (2021-06-02T02:41:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.