Papers by Sony Trenous

4 papers
A Preference-driven Paradigm for Enhanced Translation with Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Recent research shows that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) however, SFT simply instructs the model to imitate reference translations token by token, making it vulnerable to the noise present in the data.
Approach: They propose a preference-based approach to supervised fine-tuning that trains the model to imitate reference translations token by token, making it vulnerable to noise.
Outcome: The proposed approach overcomes the plateau associated with imitation-based SFT and is more resilient in the absence of gold translations.
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation (2022.naacl-main)

Copied to clipboard

Challenge: Neural Machine Translation models can be optimized to improve latency by constraining the set of output words . lexical shortlisting fails to select the right set of input words for semantically non-compositional phenomena such as idiomatic expressions.
Approach: They propose a model of vocabulary selection that constrains the set of allowed output words . they propose to increase the size of the allowed set to restore translation quality .
Outcome: The proposed model restores translation quality of an unconstrained system, as measured by human evaluations on WMT newstest2020 and idiomatic expressions, at an inference latency competitive with alignment-based selection using aggressive thresholds.
XRAG: Cross-lingual Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: XRAG evaluates the generation abilities of LLMs in cross-lingual RAG settings where the user language does not match retrieval results.
Approach: They propose a benchmark to evaluate the generation abilities of LLMs in cross-lingual RAG settings where the user language does not match retrieval results.
Outcome: XRAG is a benchmark designed to evaluate the generation abilities of LLMs in cross-lingual RAG settings where the user language does not match retrieval results.
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have made document-level machine translation increasingly practical, enabled by long-context modeling and strong generation quality.
Approach: They propose to use document-level MT followed by segment-level refinement to find the strongest and most stable improvements across six LLMs and seven language pairs.
Outcome: The proposed method outperforms error-specific prompting and evaluate-then-refine schemes in document-level translation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations