It Takes Two: A Dual Stage Approach for Terminology-Aware Translation

arXiv — cs.CL•Wednesday, November 12, 2025 at 5:00:00 AM

DuTerm represents a significant advancement in machine translation, employing a dual-stage approach that integrates a terminology-aware NMT model with a prompt-based LLM for post-editing. This innovative system was evaluated using the WMT 2025 Terminology Shared Task corpus, focusing on English-to-German, English-to-Spanish, and English-to-Russian translations. The findings reveal that the LLM's context-driven handling of terminology consistently produces superior translation quality compared to rigid constraint enforcement. This highlights a crucial trade-off in translation methodologies, suggesting that LLMs function best as context-driven mutators rather than mere generators. The implications of this research are vital for enhancing translation accuracy and efficiency in multilingual contexts, paving the way for more nuanced and adaptable translation technologies.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.LG2 days ago

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

PositiveArtificial Intelligence

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries

PositiveArtificial Intelligence

ExPairT-LLM is introduced as an exact learning algorithm aimed at improving code selection from multiple outputs generated by large language models (LLMs). Traditional code selection algorithms often struggle to identify the correct program due to misidentification of nonequivalent programs or reliance on LLMs that may not always provide accurate outputs. ExPairT-LLM addresses these issues by utilizing pairwise membership and pairwise equivalence queries, enhancing the accuracy of program selection. Evaluations show a significant improvement in success rates over existing algorithms.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go

PositiveArtificial Intelligence

The Go-UT-Bench dataset, introduced in a recent study, addresses the training data imbalance faced by code LLMs, particularly in Golang. This dataset comprises 5,264 pairs of code and unit tests sourced from 10 permissively licensed Golang repositories. The study demonstrates that fine-tuning LLMs with this dataset significantly enhances their performance, with models outperforming their base versions on over 75% of benchmark tasks.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Experience-Guided Adaptation of Inference-Time Reasoning Strategies

PositiveArtificial Intelligence

The article discusses the Experience-Guided Reasoner (EGuR), a novel AI system designed to adapt its problem-solving strategies based on experiences accumulated during inference time. Unlike existing systems that only modify textual inputs, EGuR generates tailored strategies dynamically, allowing for a more flexible approach to AI reasoning. This advancement addresses the challenge of enabling agentic AI systems to adapt their methodologies post-training.

Read full article

via arXiv — cs.LG

arXiv — cs.CL2 days ago

Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness

NeutralArtificial Intelligence

The paper titled 'Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness' discusses the capabilities of large language models (LLMs) in biomedical natural language processing (NLP) tasks. It highlights the sensitivity of LLMs to demonstration selection and addresses the hallucination issue through retrieval-augmented LLMs (RAL). However, there is a lack of rigorous evaluation of RAL's impact on various biomedical NLP tasks, which complicates understanding its capabilities in this domain.

Read full article

via arXiv — cs.CL

DEV Community3 days ago

Increase my familiarity with BASE64.

NeutralArtificial Intelligence

The article discusses BASE64, a data encoding method that has been around for 30 years. It highlights the inefficiency of BASE64, which increases data size by 33%, yet remains essential in modern applications like JSON and REST APIs. The author shares personal experiences of encountering BASE64 in various projects, emphasizing the need for a pragmatic approach to using this outdated technology.

Read full article

via DEV Community