Cover Image

Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Hanxu, Vamvas, Jannis, Sennrich, Rico
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

Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
by: Sennrich, Rico, et al.
Published: (2023)

Machine Translation Models are Zero-Shot Detectors of Translation Direction
by: Wastl, Michelle, et al.
Published: (2024)

Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models
by: Mohammadshahi, Alireza, et al.
Published: (2023)

Linear-time Minimum Bayes Risk Decoding with Reference Aggregation
by: Vamvas, Jannis, et al.
Published: (2024)

SwissBERT: The Multilingual Language Model for Switzerland
by: Vamvas, Jannis, et al.
Published: (2023)

QueST: Incentivizing LLMs to Generate Difficult Problems
by: Hu, Hanxu, et al.
Published: (2025)

SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
by: Wastl, Michelle, et al.
Published: (2025)

Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect
by: Vamvas, Jannis, et al.
Published: (2024)

DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
by: Hu, Hanxu, et al.
Published: (2026)

20min-XD: A Comparable Corpus of Swiss News Articles
by: Wastl, Michelle, et al.
Published: (2025)

Leveraging In-Context Learning for Political Bias Testing of LLMs
by: Haller, Patrick, et al.
Published: (2025)

The Mediomatix Corpus: Parallel Data for Romansh Language Varieties via Comparable Schoolbooks
by: Hopton, Zachary, et al.
Published: (2025)

Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties
by: Vamvas, Jannis, et al.
Published: (2026)

Fine-tuning the SwissBERT Encoder Model for Embedding Sentences and Documents
by: Grosjean, Juri, et al.
Published: (2024)

Robust Language Identification for Romansh Varieties
by: Model, Charlotte, et al.
Published: (2026)

Evaluating Automatic Metrics with Incremental Machine Translation Systems
by: Wu, Guojun, et al.
Published: (2024)

Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks
by: Semenov, Kirill, et al.
Published: (2025)

Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language
by: Sennrich, Kilian, et al.
Published: (2025)

RUMLEM: A Dictionary-Based Lemmatizer for Romansh
by: Fischer, Dominic P., et al.
Published: (2026)

Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples
by: Michail, Andrianos, et al.
Published: (2025)

An Analysis of BPE Vocabulary Trimming in Neural Machine Translation
by: Cognetta, Marco, et al.
Published: (2024)

Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias
by: Schuhmacher, Elias, et al.
Published: (2026)

Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?
by: Kew, Tannon, et al.
Published: (2023)

Fine-tuning Large Language Models with Sequential Instructions
by: Hu, Hanxu, et al.
Published: (2024)

Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
by: Gao, Bin, et al.
Published: (2024)

Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets
by: Moghe, Nikita, et al.
Published: (2024)

Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents
by: Wu, Shiwei, et al.
Published: (2024)

CommonMorph: Participatory Morphological Documentation Platform
by: Mahmudi, Aso, et al.
Published: (2026)

Robust Native Language Identification through Agentic Decomposition
by: Uluslu, Ahmet Yavuz, et al.
Published: (2025)

Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models
by: Ibrahim, Lujain, et al.
Published: (2025)

FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
by: Fan, Zhiting, et al.
Published: (2024)

SignCLIP: Connecting Text and Sign Language by Contrastive Learning
by: Jiang, Zifan, et al.
Published: (2024)

Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective Model
by: Niu, Fuqiang, et al.
Published: (2024)

Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models
by: Wang, Minghan, et al.
Published: (2024)

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
by: Huang, Xu, et al.
Published: (2025)

LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models
by: Hou, Ruijie, et al.
Published: (2025)

Measuring Sycophancy of Language Models in Multi-turn Dialogues
by: Hong, Jiseung, et al.
Published: (2025)

Adapting Large Language Models for Document-Level Machine Translation
by: Wu, Minghao, et al.
Published: (2024)

Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions
by: Li, Yachao, et al.
Published: (2024)

Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
by: Tong, Terry, et al.
Published: (2024)