Yang Xiang

Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models

Yu Zhang, Pingrui Zhang, Xuefeng Bai +3

Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic info…

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…

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning

Yang Xiang, Yixin Ji, Ruotao Xu +4

Large reasoning models (LRMs) have achieved remarkable performance in complex reasoning tasks, driven by their powerful inference-time scaling capability. However, LRMs often suffe…

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…

Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration

Yu Zhang, Mufan Xu, Xuefeng Bai +4

Modality following is the ability to selectively leverage multimodal contexts based on user instructions. It is fundamental to the safety and reliability of multimodal large langua…

Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models

Yang Xiang, Yixin Ji, Juntao Li +1

Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning benchmarks. However, their long chain-of-thought reasoning processes incur significant i…

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…

cs.CL2025★ 1 cited

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model

Xinping Zhao, Xinshuo Hu, Zifei Shan +14

Recent advancements in Large Language Models (LLMs)-based text embedding models primarily focus on data scaling or synthesis, yet limited exploration of training techniques and dat…

Evaluating and Steering Modality Preferences in Multimodal Large Language Model

Yu Zhang, Jinlong Ma, Yongshuai Hou +5

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit $\textbf{m…

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…

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning

Yingjie Zhu, Xuefeng Bai, Kehai Chen +3

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limi…

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.…

Beware of Calibration Data for Pruning Large Language Models

Yixin Ji, Yang Xiang, Juntao Li +5

As large language models (LLMs) are widely applied across various fields, model compression has become increasingly crucial for reducing costs and improving inference efficiency. P…

LLM-based Translation Inference with Iterative Bilingual Understanding

Andong Chen, Kehai Chen, Yang Xiang +5

The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sent…

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models

Zelin Li, Kehai Chen, Lemao Liu +4

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial a…

cs.CL2024★ 1 cited

Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving

Andong Chen, Lianzhang Lou, Kehai Chen +5

Different from the traditional translation tasks, classical Chinese poetry translation requires both adequacy and fluency in translating culturally and historically significant con…

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms

Andong Chen, Lianzhang Lou, Kehai Chen +5

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation…