5 papers
DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models
Yifan Li, Qin Li, Min Zhang
Assessing the reasoning ability of Large Language Models (LLMs) over data remains an open and pressing research question. Compared with LLMs, human reasoning can derive correspondi…
Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models
Suhang Wu, Jialong Tang, Chengyi Yang +6
Direct speech translation (ST) has garnered increasing attention nowadays, yet the accurate translation of terminology within utterances remains a great challenge. In this regard,…
Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement
Yichen Dong, Xinglin Lyu, Junhui Li +4
Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement. In this paper, we build on this idea by extending the refinemen…
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
Xinglin Lyu, Wei Tang, Yuang Li +7
Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced b…
Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusion
Bin Liu, Xinglin Lyu, Junhui Li +4
Recent studies in prompting large language model (LLM) for document-level machine translation (DMT) primarily focus on the inter-sentence context by flatting the source document in…