7 papers
G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation
Baijun Ji, Zixuan Zhou, Xiangyu Duan +4
Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and discourse-aware context sele…
PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
Sicheng Yang, Shulan Ruan, Shiwei Wu +4
While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing b…
What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
Mingyuan Fan, Yu Liu, Fuyi Wang +1
The deployment of large language models (LLMs) on resource-constrained devices remains challenging, spurring interest in split inference, where models are partitioned between clien…
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
Zhuo Chen, Xinzhe Yuan, Jianshu Zhang +8
The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). Howev…
Towards Generation-Efficient Uncertainty Estimation in Large Language Models
Mingcheng Zhu, Yu Liu, Tingting Zhu
Uncertainty estimation is important for deploying LLMs in high-stakes applications such as healthcare and finance, where hallucinations can appear fluent and plausible while being…
Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models
Hao Tang, Yu Liu, Shuanglin Yan +3
Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in…