Jinan Xu

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning

Xue Zhang, Yunlong Liang, Fandong Meng +5

Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and inter…

CM-Align: Consistency-based Multilingual Alignment for Large Language Models

Xue Zhang, Yunlong Liang, Fandong Meng +4

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically…

Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts

Xue Zhang, Yunlong Liang, Fandong Meng +4

Continually expanding new languages for existing large language models (LLMs) is a promising yet challenging approach to building powerful multilingual LLMs. The biggest challenge…

A Dual-Space Framework for General Knowledge Distillation of Large Language Models

Xue Zhang, Songming Zhang, Yunlong Liang +4

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD me…

DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translation

Zhibo Man, Yuanmeng Chen, Yujie Zhang +1

Currently, Large Language Models (LLMs) have achieved remarkable results in machine translation. However, their performance in multi-domain translation (MDT) is less satisfactory,…

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation

Songming Zhang, Xue Zhang, Tong Zhang +3

In modern large language models (LLMs), LLM alignment is of crucial importance and is typically achieved through methods such as reinforcement learning from human feedback (RLHF) a…

Warmup-Distill: Bridge the Distribution Mismatch between Teacher and Student before Knowledge Distillation

Zengkui Sun, Yijin Liu, Fandong Meng +3

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller o…

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping

Yijie Chen, Yijin Liu, Fandong Meng +3

Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identi…

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation

Chen Liang, Zhifan Feng, Zihe Liu +4

Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and…

Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words

Yijie Chen, Yijin Liu, Fandong Meng +3

Gender bias has been a focal point in the study of bias in machine translation and language models. Existing machine translation gender bias evaluations are primarily focused on ma…

Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge

Zengkui Sun, Yijin Liu, Jiaan Wang +4

Recently, Knowledge Editing has received increasing attention, since it could update the specific knowledge from outdated ones in pretrained models without re-training. However, as…

cs.CL2024★ 1 cited

LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation

Zengkui Sun, Yijin Liu, Fandong Meng +3

Multilingual neural machine translation models generally distinguish translation directions by the language tag (LT) in front of the source or target sentences. However, current LT…

Dual-Space Knowledge Distillation for Large Language Models

Songming Zhang, Xue Zhang, Zengkui Sun +2

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white…

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

Xue Zhang, Yunlong Liang, Fandong Meng +4

Multilingual knowledge editing (MKE) aims to simultaneously update factual knowledge across multiple languages within large language models (LLMs). Previous research indicates that…

Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective

Yijie Chen, Yijin Liu, Fandong Meng +3

Code generation aims to understand the problem description and generate corresponding code snippets, where existing works generally decompose such complex tasks into intermediate s…

Towards Faster k-Nearest-Neighbor Machine Translation

Xiangyu Shi, Yunlong Liang, Jinan Xu +1

Recent works have proven the effectiveness of k-nearest-neighbor machine translation(a.k.a kNN-MT) approaches to produce remarkable improvement in cross-domain translations. Howeve…

A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation

Xue Zhang, Songming Zhang, Yunlong Liang +4

Existing syntactically-controlled paraphrase generation (SPG) models perform promisingly with human-annotated or well-chosen syntactic templates. However, the difficulty of obtaini…

cs.CL2023★ 7 cited

Improving Translation Faithfulness of Large Language Models via Augmenting Instructions

Yijie Chen, Yijin Liu, Fandong Meng +3

Large Language Models (LLMs) present strong general capabilities, and a current compelling challenge is stimulating their specialized capabilities, such as machine translation, thr…

cs.CL2023★ 1 cited

Unified Model Learning for Various Neural Machine Translation

Yunlong Liang, Fandong Meng, Jinan Xu +3

Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat transla…

RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-training

Chulun Zhou, Yunlong Liang, Fandong Meng +3

Multilingual vision-language (V&L) pre-training has achieved remarkable progress in learning universal representations across different modalities and languages. In spite of recent…