Image de couverture de livre

How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chopra, Muskaan, Sparrenberg, Lorenz, Khanna, Sarthak, Sifa, Rafet
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety
par: Chopra, Muskaan, et autres
Publié: (2026)

SynCED-EnDe 2025: A Synthetic and Curated English - German Dataset for Critical Error Detection in Machine Translation
par: Chopra, Muskaan, et autres
Publié: (2025)

From Retinal Pixels to Patients: Evolution of Deep Learning Research in Diabetic Retinopathy Screening
par: Chopra, Muskaan, et autres
Publié: (2025)

Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening
par: Chopra, Muskaan, et autres
Publié: (2026)

History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting
par: Khanna, Sarthak, et autres
Publié: (2025)

Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention
par: Khanna, Sarthak, et autres
Publié: (2025)

A Survey on Current Trends and Recent Advances in Text Anonymization
par: Deußer, Tobias, et autres
Publié: (2025)

Reasoning LLMs in the Medical Domain: A Literature Survey
par: Berger, Armin, et autres
Publié: (2025)

Generalizing Abstention for Noise-Robust Learning in Medical Image Segmentation
par: Moustafa, Wesam, et autres
Publié: (2026)

Pointer-Guided Pre-Training: Infusing Large Language Models with Paragraph-Level Contextual Awareness
par: Hillebrand, Lars, et autres
Publié: (2024)

[Vision Paper] PRObot: Enhancing Patient-Reported Outcome Measures for Diabetic Retinopathy using Chatbots and Generative AI
par: Pielka, Maren, et autres
Publié: (2024)

Evaluating Consistency and Reasoning Capabilities of Large Language Models
par: Saxena, Yash, et autres
Publié: (2024)

Interpretable Topic Extraction and Word Embedding Learning using row-stochastic DEDICOM
par: Hillebrand, Lars, et autres
Publié: (2025)

Multi-Modal Vision vs. Text-Based Parsing: Benchmarking LLM Strategies for Invoice Processing
par: Berghaus, David, et autres
Publié: (2025)

AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?
par: Karmakar, Ranit, et autres
Publié: (2026)

Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations
par: Ki, Dayeon, et autres
Publié: (2024)

Generating Gender Alternatives in Machine Translation
par: Garg, Sarthak, et autres
Publié: (2024)

Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law
par: Bashir, Ali Hamza, et autres
Publié: (2026)

Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?
par: Gogoulou, Evangelia, et autres
Publié: (2025)

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization
par: Tang, Zilu, et autres
Publié: (2025)

Is continuous CoT better suited for multi-lingual reasoning?
par: Bashir, Ali Hamza, et autres
Publié: (2026)

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation
par: Huang, Xu, et autres
Publié: (2024)

Can QE-informed (Re)Translation lead to Error Correction?
par: Padmanabhan, Govardhan
Publié: (2025)

Large Language Models "Ad Referendum": How Good Are They at Machine Translation in the Legal Domain?
par: Briva-Iglesias, Vicent, et autres
Publié: (2024)

Financial Named Entity Recognition: How Far Can LLM Go?
par: Lu, Yi-Te, et autres
Publié: (2025)

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
par: Li, Bangzheng, et autres
Publié: (2023)

Small Language Model Can Self-correct
par: Han, Haixia, et autres
Publié: (2024)

Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
par: Wisniewski, Dawid, et autres
Publié: (2026)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
par: Huang, Heyan, et autres
Publié: (2024)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
par: Lu, Yi, et autres
Publié: (2025)

CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs
par: Guttmann, Kamil, et autres
Publié: (2026)

How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models
par: Corbo, Simone, et autres
Publié: (2025)

Should We be Pedantic About Reasoning Errors in Machine Translation?
par: Bao, Calvin, et autres
Publié: (2026)

Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?
par: Chiaranaipanich, Jirat, et autres
Publié: (2024)

Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
par: Berger, Armin, et autres
Publié: (2025)

Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance
par: Hillebrand, Lars, et autres
Publié: (2025)

On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?
par: Choenni, Rochelle, et autres
Publié: (2024)

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
par: Mąka, Paweł, et autres
Publié: (2025)

Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization
par: Chen, Xinran, et autres
Publié: (2024)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
par: Wang, Jingyuan, et autres
Publié: (2025)