Cover Image

Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mohammed, Wafaa, Niculae, Vlad, Zerva, Chrysoula
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation
by: Mohammed, Wafaa, et al.
Published: (2024)

On Measuring Context Utilization in Document-Level MT Systems
by: Mohammed, Wafaa, et al.
Published: (2024)

GAMBIT+: A Challenge Set for Evaluating Gender Bias in Machine Translation Quality Estimation Metrics
by: Filandrianos, Giorgos, et al.
Published: (2025)

Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs
by: Troshin, Sergey, et al.
Published: (2025)

The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation
by: Tokarchuk, Evgeniia, et al.
Published: (2023)

A Conformal Risk Control Framework for Granular Word Assessment and Uncertainty Calibration of CLIPScore Quality Estimates
by: Gomes, Gonçalo, et al.
Published: (2025)

Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
by: Tokarchuk, Evgeniia, et al.
Published: (2026)

Angular Dispersion Accelerates $k$-Nearest Neighbors Machine Translation
by: Tokarchuk, Evgeniia, et al.
Published: (2025)

Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?
by: Gomes, Gonçalo, et al.
Published: (2025)

Non-Exchangeable Conformal Language Generation with Nearest Neighbors
by: Ulmer, Dennis, et al.
Published: (2024)

On the Low-Rank Parametrization of Reward Models for Controlled Language Generation
by: Troshin, Sergey, et al.
Published: (2024)

SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions
by: Thomas, Konstantinos, et al.
Published: (2026)

"I Never Said That": A dataset, taxonomy and baselines on response clarity classification
by: Thomas, Konstantinos, et al.
Published: (2024)

kNN For Whisper And Its Effect On Bias And Speaker Adaptation
by: Nachesa, Maya K., et al.
Published: (2024)

Your Multimodal Speech Model Says I Have a Face for Radio
by: Nachesa, Maya K., et al.
Published: (2026)

Calibrating Translation Decoding with Quality Estimation on LLMs
by: Wu, Di, et al.
Published: (2025)

Asking a Language Model for Diverse Responses
by: Troshin, Sergey, et al.
Published: (2025)

Teaching Language Models to Faithfully Express their Uncertainty
by: Eikema, Bryan, et al.
Published: (2025)

Conformal Prediction for Natural Language Processing: A Survey
by: Campos, Margarida M., et al.
Published: (2024)

Quality-Aware Decoding: Unifying Quality Estimation and Decoding
by: Koneru, Sai, et al.
Published: (2025)

Rejected Dialects: Biases Against African American Language in Reward Models
by: Mire, Joel, et al.
Published: (2025)

Do Language Models Reason Across Languages?
by: Meng, Yan, et al.
Published: (2026)

Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering
by: Allbert, Rumi, et al.
Published: (2024)

Translating With Feeling: Centering Translator Perspectives within Translation Technologies
by: Chechelnitsky, Daniel, et al.
Published: (2026)

Findings of the WMT 2024 Shared Task on Chat Translation
by: Mohammed, Wafaa, et al.
Published: (2024)

Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set
by: Eichin, Florian, et al.
Published: (2025)

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation
by: Khalil, Mohammed, et al.
Published: (2024)

A Retrieval-Based Approach to Medical Procedure Matching in Romanian
by: Niculae, Andrei, et al.
Published: (2025)

Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
by: Chen, Andong, et al.
Published: (2025)

AdaSplash-2: Faster Differentiable Sparse Attention
by: Gonçalves, Nuno, et al.
Published: (2026)

RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs
by: Nguyen, Tuan T., et al.
Published: (2025)

LatentQA: Teaching LLMs to Decode Activations Into Natural Language
by: Pan, Alexander, et al.
Published: (2024)

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs
by: Chen, Keyu, et al.
Published: (2025)

Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs
by: Li, Junyi Jessy, et al.
Published: (2026)

LLMs Are Zero-Shot Context-Aware Simultaneous Translators
by: Koshkin, Roman, et al.
Published: (2024)

Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key
by: Chen, Yingda, et al.
Published: (2024)

Unlocking Fine-Grained Translation Quality Estimation in LRMs through Synergistically Evolving Implicit and Explicit Reasoning
by: Dang, Renfei, et al.
Published: (2026)

Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation
by: Sharami, Javad Pourmostafa Roshan, et al.
Published: (2024)

Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence
by: Liu, Yinhong, et al.
Published: (2024)

Task-Aware Calibration: Provably Optimal Decoding in LLMs
by: Tomov, Tim, et al.
Published: (2026)