Copertina

Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gisserot-Boukhlef, Hippolyte, Rei, Ricardo, Malherbe, Emmanuel, Hudelot, Céline, Colombo, Pierre, Guerreiro, Nuno M.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
di: Gisserot-Boukhlef, Hippolyte, et al.
Pubblicazione: (2026)

Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
di: Gisserot-Boukhlef, Hippolyte, et al.
Pubblicazione: (2024)

When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance
di: Boizard, Nicolas, et al.
Pubblicazione: (2025)

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs
di: Boizard, Nicolas, et al.
Pubblicazione: (2026)

Should We Still Pretrain Encoders with Masked Language Modeling?
di: Gisserot-Boukhlef, Hippolyte, et al.
Pubblicazione: (2025)

EuroBERT: Scaling Multilingual Encoders for European Languages
di: Boizard, Nicolas, et al.
Pubblicazione: (2025)

EuroLLM-22B: Technical Report
di: Ramos, Miguel Moura, et al.
Pubblicazione: (2026)

Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation
di: Himmi, Anas, et al.
Pubblicazione: (2024)

Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation
di: Pombal, José, et al.
Pubblicazione: (2025)

Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation
di: Agrawal, Sweta, et al.
Pubblicazione: (2024)

Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral
di: Farinhas, António, et al.
Pubblicazione: (2025)

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
di: Boizard, Nicolas, et al.
Pubblicazione: (2024)

Analyzing Context Contributions in LLM-based Machine Translation
di: Zaranis, Emmanouil, et al.
Pubblicazione: (2024)

CroissantLLM: A Truly Bilingual French-English Language Model
di: Faysse, Manuel, et al.
Pubblicazione: (2024)

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors
di: Treviso, Marcos, et al.
Pubblicazione: (2024)

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs
di: Rei, Ricardo, et al.
Pubblicazione: (2025)

Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models
di: Pombal, José, et al.
Pubblicazione: (2025)

Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study
di: Agrawal, Aryan, et al.
Pubblicazione: (2025)

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
di: Alves, Duarte M., et al.
Pubblicazione: (2024)

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
di: Aswal, Darpan, et al.
Pubblicazione: (2025)

Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
di: Pombal, José, et al.
Pubblicazione: (2026)

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
di: Sun, Shuqiao, et al.
Pubblicazione: (2024)

EuroLLM: Multilingual Language Models for Europe
di: Martins, Pedro Henrique, et al.
Pubblicazione: (2024)

ColPali: Efficient Document Retrieval with Vision Language Models
di: Faysse, Manuel, et al.
Pubblicazione: (2024)

MindEval: Benchmarking Language Models on Multi-turn Mental Health Support
di: Pombal, José, et al.
Pubblicazione: (2025)

TODO: Enhancing LLM Alignment with Ternary Preferences
di: Guo, Yuxiang, et al.
Pubblicazione: (2024)

Word Alignment as Preference for Machine Translation
di: Wu, Qiyu, et al.
Pubblicazione: (2024)

Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughts
di: Luo, Xianzhen, et al.
Pubblicazione: (2024)

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
di: Rozanov, Nikolai, et al.
Pubblicazione: (2024)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
di: Zhang, Xuemiao, et al.
Pubblicazione: (2025)

Can Automatic Metrics Assess High-Quality Translations?
di: Agrawal, Sweta, et al.
Pubblicazione: (2024)

EuroLLM-9B: Technical Report
di: Martins, Pedro Henrique, et al.
Pubblicazione: (2025)

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
di: Bernas, Raphael, et al.
Pubblicazione: (2026)

Is Context Helpful for Chat Translation Evaluation?
di: Agrawal, Sweta, et al.
Pubblicazione: (2024)

Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
di: Moslonka, Charles, et al.
Pubblicazione: (2025)

Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
di: Sun, Zetian, et al.
Pubblicazione: (2025)

StreaMulT: Streaming Multimodal Transformer for Heterogeneous and Arbitrary Long Sequential Data
di: Pellegrain, Victor, et al.
Pubblicazione: (2021)

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
di: Hu, Zhengyu, et al.
Pubblicazione: (2026)

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
di: Cheng, Pengyu, et al.
Pubblicazione: (2023)

TEGRA: Text Encoding With Graph and Retrieval Augmentation for Misinformation Detection
di: Faye, Géraud, et al.
Pubblicazione: (2026)