MENT benchmark plus RATE agentic evaluator raise combined system- and segment-level correlation with human judgments by at least 3.2 points over prior MT metrics and LLM judges.
https://arxiv.org/abs/2509.05209
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Synthetic linguistic reasoning traces improve low-resource machine translation most when supplied as reliable in-context guidance, but produce smaller and less consistent gains when used as training data for fine-tuning.
An RL-trained translation agent that searches Wiktionary during reasoning improves neologism translation, and the new Neko benchmark covers 16 languages and 75 directions.
HydraQE is a new end-to-end speech translation QE system using Qwen3-ASR backbone, sparsemax layer mixing, bidirectional Transformer, and multi-task curriculum training on human and pseudo labels that outperforms cascaded baselines.
A Bayesian calibration technique lets production teams compare replacement LLMs reliably using limited human feedback on correctness, refusal, and style.
Compact 0.8B-7B models for bidirectional Japanese-English translation outperform large multilingual models on real-world domain benchmarks.
A literature survey that organizes prompting, fine-tuning, preference optimization, and context-aware techniques for LLM-based machine translation with emphasis on low-resource languages.
citing papers explorer
-
Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation
MENT benchmark plus RATE agentic evaluator raise combined system- and segment-level correlation with human judgments by at least 3.2 points over prior MT metrics and LLM judges.
-
Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?
Synthetic linguistic reasoning traces improve low-resource machine translation most when supplied as reliable in-context guidance, but produce smaller and less consistent gains when used as training data for fine-tuning.
-
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
An RL-trained translation agent that searches Wiktionary during reasoning improves neologism translation, and the new Neko benchmark covers 16 languages and 75 directions.
-
HydraQE: OSU's Submission for the IWSLT 2026 Speech Translation Metrics Shared Task
HydraQE is a new end-to-end speech translation QE system using Qwen3-ASR backbone, sparsemax layer mixing, bidirectional Transformer, and multi-task curriculum training on human and pseudo labels that outperforms cascaded baselines.
-
When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
A Bayesian calibration technique lets production teams compare replacement LLMs reliably using limited human feedback on correctness, refusal, and style.
-
CAT-Translate: Building Compact Open-Source Models for Japanese-English Translation
Compact 0.8B-7B models for bidirectional Japanese-English translation outperform large multilingual models on real-world domain benchmarks.
-
Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
A literature survey that organizes prompting, fine-tuning, preference optimization, and context-aware techniques for LLM-based machine translation with emphasis on low-resource languages.