Cover Image

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Finkelstein, Mara, Naskar, Subhajit, Mirzazadeh, Mehdi, Shah, Apurva, Freitag, Markus
Format:	Preprint
Published:	2023
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data
by: Finkelstein, Mara, et al.
Published: (2024)

Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
by: Trabelsi, Firas, et al.
Published: (2024)

Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
by: Tomani, Christian, et al.
Published: (2023)

Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
by: Zhang, Lily H., et al.
Published: (2024)

MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task
by: Juraska, Juraj, et al.
Published: (2024)

Position: The Most Expensive Part of an LLM should be its Training Data
by: Kandpal, Nikhil, et al.
Published: (2025)

Direct Neural Machine Translation with Task-level Mixture of Experts models
by: Tourni, Isidora Chara, et al.
Published: (2023)

From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set
by: Finkelstein, Mara, et al.
Published: (2024)

Making the Most of your Model: Methods for Finetuning and Applying Pretrained Transformers
by: Yoshida, Davis
Published: (2024)

MQM Re-Annotation: A Technique for Collaborative Evaluation of Machine Translation
by: Riley, Parker, et al.
Published: (2025)

Generating Difficult-to-Translate Texts
by: Zouhar, Vilém, et al.
Published: (2025)

Maastricht University at AMIYA: Adapting LLMs for Dialectal Arabic using Fine-tuning and MBR Decoding
by: Alali, Abdulhai, et al.
Published: (2026)

MetricX-25 and GemSpanEval: Google Translate Submissions to the WMT25 Evaluation Shared Task
by: Juraska, Juraj, et al.
Published: (2025)

Mitigating Metric Bias in Minimum Bayes Risk Decoding
by: Kovacs, Geza, et al.
Published: (2024)

Go-Browse: Training Web Agents with Structured Exploration
by: Gandhi, Apurva, et al.
Published: (2025)

LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
by: Xu, Wenda, et al.
Published: (2023)

SpeechQE: Estimating the Quality of Direct Speech Translation
by: Han, HyoJung, et al.
Published: (2024)

AskQE: Question Answering as Automatic Evaluation for Machine Translation
by: Ki, Dayeon, et al.
Published: (2025)

Sparse Memory Finetuning as a Low-Forgetting Alternative to LoRA and Full Finetuning
by: Gupta, Prakhar, et al.
Published: (2026)

Improving Sparse Memory Finetuning
by: Goyal, Satyam, et al.
Published: (2026)

Pretraining Strategies using Monolingual and Parallel Data for Low-Resource Machine Translation
by: Nguefack, Idriss Nguepi, et al.
Published: (2025)

Assessing the Portability of Parameter Matrices Trained by Parameter-Efficient Finetuning Methods
by: Sabry, Mohammed, et al.
Published: (2024)

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
by: Hong, Fenglu, et al.
Published: (2025)

ThinkQE: Query Expansion via an Evolving Thinking Process
by: Lei, Yibin, et al.
Published: (2025)

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

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
by: Zhang, Biao, et al.
Published: (2024)

Improving Cross-Cultural Survey Simulation with Calibrated Value Personas
by: Abels, Axel, et al.
Published: (2026)

SoftQE: Learned Representations of Queries Expanded by LLMs
by: Pimpalkhute, Varad, et al.
Published: (2024)

Fast Best-of-N Decoding via Speculative Rejection
by: Sun, Hanshi, et al.
Published: (2024)

QE4PE: Word-level Quality Estimation for Human Post-Editing
by: Sarti, Gabriele, et al.
Published: (2025)

QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation
by: Yoo, Gahyun, et al.
Published: (2024)

Training Versatile Coding Agents in Synthetic Environments
by: Zhu, Yiqi, et al.
Published: (2025)

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
by: Geng, Saibo, et al.
Published: (2023)

Beyond Human-Only: Evaluating Human-Machine Collaboration for Collecting High-Quality Translation Data
by: Liu, Zhongtao, et al.
Published: (2024)

From Scratch to Fine-Tuned: A Comparative Study of Transformer Training Strategies for Legal Machine Translation
by: Barman, Amit, et al.
Published: (2025)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
by: Phan, Phuc, et al.
Published: (2024)

CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs
by: Guttmann, Kamil, et al.
Published: (2026)

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
by: Longpre, Shayne, et al.
Published: (2025)

Decoding News Bias: Multi Bias Detection in News Articles
by: Shah, Bhushan Santosh, et al.
Published: (2025)

AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
by: Guo, Taicheng, et al.
Published: (2026)