9 papers
DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
Hongbin Zhang, Junhao Liu, Xuefeng Bai +3
Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-language text, to increasingly ado…
Unlocking Proactivity in Task-Oriented Dialogue
Azure Zhang, Ning Gao, Yuqin Dai +7
Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance wi…
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
Hongbin Zhang, Chaozheng Wang, Kehai Chen +4
On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference…
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
Hongbin Zhang, Kehai Chen, Xuefen Bai +4
Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is cha…
Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
Hongbin Zhang, Kehai Chen, Xuefeng Bai +2
Reward models (RMs) are crucial for aligning large language models (LLMs) with diverse cultures. Consequently, evaluating their cultural awareness is essential for further advancin…
Exploring the Translation Mechanism of Large Language Models
Hongbin Zhang, Kehai Chen, Xuefeng Bai +3
While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remai…
LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
Hongbin Zhang, Kehai Chen, Xuefeng Bai +2
Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data.…
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
Hongbin Zhang, Kehai Chen, Xuefeng Bai +2
Large language models (LLMs) have showcased impressive multilingual machine translation ability. However, unlike encoder-decoder style models, decoder-only LLMs lack an explicit al…
Improving CTC-AED model with integrated-CTC and auxiliary loss regularization
Daobin Zhu, Xiangdong Su, Hongbin Zhang
Connectionist temporal classification (CTC) and attention-based encoder decoder (AED) joint training has been widely applied in automatic speech recognition (ASR). Unlike most hybr…