Papers by Xuebo Liu

Self-Powered LLM Modality Expansion for Large Speech-Text Models (2024.emnlp-main)

Challenge:	Current studies have focused on fine-tuning, but the use of instruction tuning is not as effective as fine-cuning.
Approach:	They propose a commonality-aware instruction tuning strategy to cluster instruction datasets into distinct groups with three proposed metrics Task, Embedding and Length.
Outcome:	The proposed strategy boosts an average improvement of 2.1% on the general domain and 5.2% on the special domain.

Copied to clipboard

Tengfei Yu, Xuebo Liu, Zhiyi Hou, Liang Ding, Dacheng Tao, Min Zhang

Multimodality

Challenge:	Large language models exhibit remarkable performance across diverse tasks . however, these methods require significant resource demands and tend to overfit specific tasks.
Approach:	They propose a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning.
Outcome:	The proposed model mitigates speech anchor bias and improves the fusion of speech and text modalities in large language models.

Progressive Multi-Granularity Training for Non-Autoregressive Translation (2021.findings-acl)

Copied to clipboard

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

Norm-Based Curriculum Learning for Neural Machine Translation (2020.acl-main)

Challenge:	Non-autoregressive translation models are weak at learning high-mode knowledge, argues a new study . despite the improved learning difficulty, there are still complicated word orders and structures in the synthetic sentences, making the NAT performance sub-optimal.
Approach:	They propose to train non-autoregressive translation models to learn fine-grained lower-mode knowledge . they break down sentence-level examples into three types and increase granularities .
Outcome:	The proposed method improves phrase translation accuracy and model reordering ability against strong NAT baselines.

Copied to clipboard

Xuebo Liu, Houtim Lai, Derek F. Wong, Lidia S. Chao

Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning (2026.findings-acl)

Challenge:	Experimental results show that the proposed method outperforms strong baselines in terms of BLEU score (+1.17/+1.56) and training speedup (2.22x/3.33x).
Approach:	They propose a norm-based curriculum learning method that measures difficulty, competence and weight of a sentence in a word embedding.
Outcome:	The proposed method outperforms baselines in terms of BLEU score (+1.17/+1.56) and training speedup (2.22x/3.33x).

Copied to clipboard

Jun Rao, Xuebo Liu, Hexuan Deng, Zepeng Lin, Zixiong Yu, Jiansheng Wei, Xiaojun Meng, Min Zhang

Reasoning

Challenge:	Current data selection paradigms rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training.
Approach:	They propose a dynamic sampling framework that aligns training data with the model's intrinsic competence by iterating on real-time feedback.
Outcome:	Extensive experiments on eight benchmarks show that SAI-DPO outperforms static baselines at most nearly 6 points, achieving state-of-the-art efficiency with significantly less data.

Difficulty-Aware Machine Translation Evaluation (2021.acl-short)

Copied to clipboard

Runzhe Zhan, Xuebo Liu, Derek F. Wong, Lidia S. Chao

AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration (2025.findings-emnlp)

Challenge:	Current MT evaluation measures pay the same attention to each sentence component . in real-world examinations, the questions vary in difficulty and weightings .
Approach:	They propose a difficulty-aware MT evaluation metric that takes translation difficulty into account . they propose to use this metric to evaluate machine translation (MT) results .
Outcome:	The proposed method outperforms most MT evaluation metrics in terms of human correlation.

Copied to clipboard

Chunhao Tian, Yutong Wang, Xuebo Liu, Zhexuan Wang, Liang Ding, Miao Zhang, Min Zhang

Green & Sustainable NLP

Challenge:	Existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages.
Approach:	They propose to use a Natural Language to Format mechanism to optimize the structure of agent teams and incorporate a natural language to format mechanism to ensure consistency and standardization.
Outcome:	The proposed method outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks while reducing token consumption.

DB-LLM: Accurate Dual-Binarization for Efficient LLMs (2024.findings-acl)

Copied to clipboard

Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, Dacheng Tao

Green & Sustainable NLP

Challenge:	Existing methods for ultra-low bit quantization cause severe accuracy drops . a novel Dual-Binarization method is proposed for efficient Large Language Models .
Approach:	They propose a Dual-Binarization method that takes 2-bit-width and binarization into account . they propose DB-LLM, which uses a 2-bit binarized weighted model to represent weights efficiently .
Outcome:	The proposed method surpasses the current State-of-the-Art in ultra-low bit quantization and achieves 20% reduction in computational consumption compared to the SOTA method under the same bit-width.

Revisiting Token Dropping Strategy in Efficient BERT Pretraining (2023.acl-long)

Copied to clipboard

Qihuang Zhong, Liang Ding, Juhua Liu, Xuebo Liu, Min Zhang, Bo Du, Dacheng Tao

AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration (2025.acl-long)

Challenge:	Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT.
Approach:	They propose a semantic-consistent learning method to improve token dropping by skipping the computation of a subset of input tokens at several middle layers.
Outcome:	The proposed method achieves consistent and significant performance gains across all tasks and model sizes.

Copied to clipboard

Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, Min Zhang

Responsible & Trustworthy NLP

Challenge:	Existing methods for MAS suffer from high token consumption and inefficiency due to frequent generation and communication among multiple agents.
Approach:	They propose a multi-agent system based on large language models that identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance.
Outcome:	The proposed method reduces prompt token consumption and completion token consumption by 18.4% and improves task performance by 1.14.

DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning (2026.acl-long)

Copied to clipboard

Rongqing Jiang, Xuebo Liu, Shengxin Liu, Yutong Wang, Min Zhang, Shimin Tao, Daimeng Wei, Min Zhang

Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)

Challenge:	Existing approaches to idiom translation are limited by the constraints of static parametric memory and retrieval noise . idiomatic expressions are non-compositional units where figurative meanings diverge from literal interpretations .
Approach:	They propose a detect-retrieve-arbitrate framework that detects idiomatic spans by reasoning over semantic conflicts between literal and contextual meanings.
Outcome:	The proposed framework improves GPT-5-mini and Emerging Slang datasets on various model scales.

Copied to clipboard

Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang

Curriculum Consistency Learning for Conditional Sentence Generation (2024.emnlp-main)

Challenge:	Large language models have been widely adopted in natural language processing, yet they produce unreliable content.
Approach:	They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data.
Outcome:	The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods.

Copied to clipboard

Liangxin Liu, Xuebo Liu, Lian Lian, Shengjun Cheng, Jun Rao, Tengfei Yu, Hexuan Deng, Min Zhang

Text Generation

Challenge:	Consistency learning (CL) has proven to be a valuable technique for improving the robustness of conditional sentence generation models.
Approach:	They propose a strategy that guides models to learn consistency in alignment with their current capacity to differentiate between features.
Outcome:	The proposed strategy delivers +2.0 accuracy point improvement compared with vanilla IT and +0.7 COMET scores over traditional CL methods in MT tasks.

LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models (2024.acl-long)

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie

Robustness in NLP

Challenge:	Existing methods for post-training quantization (PTQ) are limited by the complexity of the quantization parameter and performance degradations when tested on unseen datasets.
Approach:	They propose a learnable smooth-based PTQ framework that allows for rapid adaptation during testing.
Outcome:	The proposed framework improves performance on unseen datasets and reduces memory constraints.

CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task (2025.findings-emnlp)

Copied to clipboard

Haosi Mo, Xinyu Ma, Xuebo Liu, Derek F. Wong, Yu Li, Jie Liu, Min Zhang

Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner (2024.emnlp-main)

Challenge:	Existing benchmarks focus on isolated abilities, lacking a holistic framework for assessing LLM capabilities.
Approach:	They propose a Cognition-Domain-Task framework which measures a model’s capabilities across three dimensions.
Outcome:	The proposed framework improves performance on dataset evaluation and data selection, while achieving higher scores on general and specific benchmarks.

Copied to clipboard

Shudong Liu, Zhaocong Li, Xuebo Liu, Runzhe Zhan, Derek Wong, Lidia Chao, Min Zhang

Challenge:	Large language models (LLMs) exhibit excessive, random, and uninformative uncertainty rendering them unsuitable for decision-making in human-computer interactions.
Approach:	They propose an uncertainty-aware instruction tuning method that aligns LLMs’ perception with the probabilistic uncertainty of the generation.
Outcome:	The proposed method improves LLMs' performance by 45.2%, with reasonably good out-of-domain generalization capabilities.

Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore (2025.coling-main)

Copied to clipboard

Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xuebo Liu, Lidia S. Chao, Min Zhang

Low-Resource NLP

Challenge:	Existing methods for detecting LLM-generated text require no training data.
Approach:	They propose a black-box zero-shot detection approach that calculates the Grammar Error Correction Score for a given text to differentiate between human-written and LLM-generated texts.
Outcome:	The proposed method outperforms current state-of-the-art zero-shot and supervised methods, achieving an average AUROC of 98.62% across XSum and Writing Prompts datasets.

Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling (2022.emnlp-main)

Copied to clipboard

Zhijun Wang, Xuebo Liu, Min Zhang

Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models (2025.emnlp-main)

Challenge:	Existing research treats Chinese character as a minimum unit for representation . however, such representation suffers from two bottlenecks: 1) learning bottleneck; 2) parameter bottleneck, each individual character has to be represented by a unique vector.
Approach:	They propose a representation method for Chinese characters to break the representation bottlenecks . they map each stroke to a specific Latin character, thus allowing similar Chinese characters .
Outcome:	The proposed representation method breaks two representation bottlenecks in Chinese character representation . it maps each stroke to a specific Latin character, thus allowing similar Chinese characters to have similar representations .

Copied to clipboard

Ming Wang, Miao Zhang, Xuebo Liu, Liqiang Nie

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation (2026.findings-acl)

Challenge:	Existing activation sparsification methods rely on activation magnitude and weights for sparsity . authors propose a weight-aware activation-a-ware framework for large language models .
Approach:	They propose a weight-aware activation sparsity framework that uses weight-based scoring to measure activation importance in sparsification and a custom GPU sparse kernel to support it.
Outcome:	The proposed framework outperforms existing methods at 60% model-level sparsity and significantly outperfies them at higher sparsities.

Copied to clipboard

Junlin Li, Shuangyong Song, Guodong DU, Ngai Wong, Xuebo Liu, Yongxiang Li, Min Zhang, Jing Li, Xuelong Li

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Challenge:	Existing methods for fine-tuned large language models fail on fine-scale datasets . large data scale amplifies delta parameter magnitude, singular values, and entropy, causing compression errors.
Approach:	They propose a training- and data-free delta compression method that captures dominant delta structure and compensates residual low-rank approximation to recover fine-grained details from smaller residual error.
Outcome:	The proposed method outperforms existing methods on large-scale datasets on dense and MoE architectures.

Copied to clipboard

Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, Min Zhang

Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation (2024.findings-acl)

Challenge:	Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach:	They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome:	The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.

Copied to clipboard

Zhexuan Wang, Shudong Liu, Xuebo Liu, Miao Zhang, Derek Wong, Min Zhang

Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization (2023.emnlp-main)

Challenge:	Existing methods to transfer knowledge from kNN datastore into new models are expensive and arbitrarily transfer knowledge.
Approach:	They propose a domain-aware method which filters out domain-relevant neighborhood knowledge for learning in the distillation process.
Outcome:	The proposed method achieves state-of-the-art on four domain translation tasks.

Copied to clipboard

Chi Cheang, Hou Chan, Derek Wong, Xuebo Liu, Zhaocong Li, Yanming Sun, Shudong Liu, Lidia Chao

Information Extraction & Text Mining

Challenge:	Existing summarization benchmarks overlap in time with pre-training corpora and fine-tuning datasets.
Approach:	They propose a temporal generalization benchmark that contains data samples from 2010 to 2022 to understand the temporal ability of abstractive summarization models.
Outcome:	The proposed benchmark analyzes data samples from 2010 to 2022 to understand the temporal generalization ability of abstractive summarization models.

TransGEC: Improving Grammatical Error Correction with Translationese (2023.findings-acl)

Copied to clipboard

Tao Fang, Xuebo Liu, Derek F. Wong, Runzhe Zhan, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang

DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization (2025.acl-long)

Challenge:	Experimental results show that data augmentation improves accuracy over strong baselines.
Approach:	They propose to use translationese as input for GEC data augmentation to overcome stylistic discrepancies . they propose to obtain human-translated texts with a more similar style to non-native texts .
Outcome:	The proposed method improves correction accuracy over strong baselines on four GEC benchmarks.

Copied to clipboard

Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Jing Li, Min Zhang, Zhaopeng Tu

Responsible & Trustworthy NLP

Challenge:	Structured pruning reduces model size but often causes uneven degradation across domains, leading to biased performance.
Approach:	They propose a method that dynamically adjusts the data distribution during training to restore balanced performance across heterogeneous and multi-tasking data.
Outcome:	Experiments in monolingual and multilingual settings show that the proposed method surpasses similarly sized models in pruning and continued pretraining over perplexity, downstream tasks, and instruction tuning.

UnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content Generation (2025.findings-acl)

Copied to clipboard

SongTang SongTang, Kaiyong Zhao, Lei Wang, Yuliang Li, Xuebo Liu, Junyi Zou, Qiang Wang, Xiaowen Chu

Challenge:	UnrealLLM is a novel framework that connects natural language descriptions with the professional PCG system (Unreal Engine 5) to automate scene generation.
Approach:	They propose a novel multi-agent framework that connects natural language descriptions with the professional PCG system (Unreal Engine 5) to automate scene generation.
Outcome:	The proposed framework achieves competitive performance in technical metrics and aesthetic quality, offering unique advantages in generation scale and interactivity.

ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Zhaocong Li, Xuebo Liu, Derek F. Wong, Lidia S. Chao, Min Zhang

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)

Challenge:	Existing transfer learning methods for low-resource NMT are static, which simply transfer knowledge from a parent model to a child model once via parameter initialization.
Approach:	They propose a transfer learning method that can continuously transfer knowledge from the parent model during the training of the child model.
Outcome:	The proposed method can transfer knowledge from the parent model to the child model during the training of the child.

Copied to clipboard

Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Revisiting Demonstration Selection Strategies in In-Context Learning (2024.acl-long)

Challenge:	Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities.
Approach:	They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base.
Outcome:	The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods.

Copied to clipboard

Keqin Peng, Liang Ding, Yancheng Yuan, Xuebo Liu, Min Zhang, Yuanxin Ouyang, Dacheng Tao

Low-Resource NLP

Challenge:	Large language models (LLMs) have shown an impressive ability to perform a wide range of tasks using in-context learning (ICL).
Approach:	They propose a data- and model-dependent method to select models using in-context learning, TopK + ConE, and propose unified explanations for the effectiveness of previous methods.
Outcome:	The proposed method improves language understanding and generation tasks with different model scales.

On the Copying Behaviors of Pre-Training for Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Xuebo Liu, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Shuming Shi, Zhaopeng Tu

Revisiting Commonsense Reasoning in Machine Translation: Training, Evaluation and Challenge (2023.acl-long)

Challenge:	Existing studies show that initializing NMT models with pre-trained language models (LM) can speed up the model training and boost the model performance.
Approach:	They propose a method to control copying behaviors in NMT models by initializing them with pre-trained language models (LM) they propose to use a metric called copy ratio to control the copying behavior in decoding.
Outcome:	The proposed method improves translation performance by controlling copying behaviors for pre-training based models.

Copied to clipboard

Xuebo Liu, Yutong Wang, Derek F. Wong, Runzhe Zhan, Liangxuan Yu, Min Zhang

Reasoning

Challenge:	CR is the ability to understand and navigate the world using basic knowledge and understanding shared by most people.
Approach:	They propose to incorporate pretrained knowledge into NMT models and use them as robust testbeds for investigating CR in NMT.
Outcome:	The proposed method improves the training of NMT models with high CR abilities and provides accurate evaluation metrics.

On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation (2021.findings-emnlp)

Copied to clipboard

Xuebo Liu, Longyue Wang, Derek F. Wong, Liang Ding, Lidia S. Chao, Shuming Shi, Zhaopeng Tu

Pluggable Neural Machine Translation Models via Memory-augmented Adapters (2024.lrec-main)

Challenge:	Experimental results show that PT and BT are nicely complementary to each other.
Approach:	They introduce two probing tasks for PT and BT respectively and investigate their complementarity.
Outcome:	The proposed methods establish state-of-the-art on the WMT16 English-Romanian and English-Russian benchmarks.

Copied to clipboard

Yuzhuang Xu, Shuo Wang, Peng Li, Xuebo Liu, Xiaolong Wang, Weidong Liu, Yang Liu

SGIC: A Self-Guided Iterative Calibration Framework for RAG (2025.acl-long)

Challenge:	Recent years, neural machine translation systems are often developed with large-scale parallel data extracted from the Web.
Approach:	They propose a memory-augmented adapter to steer pretrained neural machine translation models in a pluggable manner by combining model representations and retrieved results.
Outcome:	The proposed method outperforms several representative pluggable baselines on style- and domain-specific experiments.

Copied to clipboard

Guanhua Chen, Yutong Yao, Lidia S. Chao, Xuebo Liu, Derek F. Wong

Information Retrieval

Challenge:	Existing studies on retrieval-augmented generation (RAG) focus on extracting relevant documents or refinement of specialized instructions.
Approach:	They propose a framework that provides LLMs with specific cues to improve their calibration efficacy . they propose an iterative self-calibration training set that harnesses uncertainty scores .
Outcome:	The proposed framework significantly improves performance on both closed-source and open-source LLMs.

PromptST: Abstract Prompt Learning for End-to-End Speech Translation (2023.emnlp-main)

Copied to clipboard

Tengfei Yu, Liang Ding, Xuebo Liu, Kehai Chen, Meishan Zhang, Dacheng Tao, Min Zhang

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)

Challenge:	Experimental results show that PromptST can improve speech-to-text translation by capturing richer linguistic knowledge.
Approach:	They propose a plug-in prompt-enhanced S2T model that captures richer linguistic knowledge . they use a 10GB linguistic probing benchmark to investigate the fusion of speech and text features .
Outcome:	The proposed model can improve on a strong baseline by capturing richer linguistic knowledge.

Copied to clipboard

Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Robustness in NLP

Challenge:	Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning.
Approach:	SeaPO introduces error types commonly occurring in large language models to improve preference learning.
Outcome:	SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors .

DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding (2020.findings-emnlp)

Copied to clipboard

Zilong Wang, Mingjie Zhan, Xuebo Liu, Ding Liang

Multimodality

Challenge:	Form understanding is a complex task because of the textual contents and organizational structure of forms.
Approach:	They propose to use multimodal methods to extract key-value pairs from forms . they validate their method on two benchmarks and demonstrate their effectiveness .
Outcome:	The proposed method is validated on two benchmarks, MedForm and FUNSD.

Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation (2021.acl-long)

Copied to clipboard

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu

Towards Demonstration-Aware Large Language Models for Machine Translation (2024.findings-acl)

Challenge:	Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation models.
Approach:	They propose to use knowledge distillation to generate training data for non-autoregressive translation models by leveraging pretraining.
Outcome:	The proposed approach achieves 28.2 and 33.9 BLEU points on the WMT14 English-German and WMT16 Romanian-English datasets.

Copied to clipboard

Chen Li, Meishan Zhang, Xuebo Liu, Zhaocong Li, Derek Wong, Min Zhang

LPZero: Language Model Zero-cost Proxy Search from Zero (2024.findings-emnlp)

Challenge:	Large language models for machine translation often face difficulties in leveraging demonstrations to further improve their performance.
Approach:	They propose a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs.
Outcome:	The proposed model integrates demonstration-aware training and inference strategies within tuning-based LTMs.

Copied to clipboard

Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, Xiaowen Chu

kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine Translation (2023.acl-long)

Challenge:	Existing zero-cost (ZC) proxies rely on expert knowledge and incur significant trial-and-error costs.
Approach:	They propose a framework that automatically designs zero-cost (ZC) proxies for various tasks and incorporates genetic programming to find the optimal symbolic composition.
Outcome:	The proposed framework achieves higher ranking consistency than human-designed proxies on NLP tasks.

Copied to clipboard

Shudong Liu, Xuebo Liu, Derek F. Wong, Zhaocong Li, Wenxiang Jiao, Lidia S. Chao, Min Zhang

Revisiting Grammatical Error Correction Evaluation and Beyond (2022.emnlp-main)

Challenge:	Transfer learning is an effective technique for enhancing low-resource neural machine translation (NMT) however, these methods do not make use of the parent knowledge during the child inference, which may limit the translation performance.
Approach:	They propose a k-Nearest-Neighbor Transfer Learning approach which leverages the parent knowledge throughout the entire developing process of the child model.
Outcome:	The proposed approach outperforms strong baselines on four low-resource translation tasks.

Copied to clipboard

Peiyuan Gong, Xuebo Liu, Heyan Huang, Min Zhang

Syntactic Text Processing

Challenge:	Pretraining-based (PT) evaluation metrics are not effective for training grammatical error correction systems.
Approach:	They propose a pretraining-based GEC evaluation metric which only uses PT-based metrics to score the corrected parts of the system.
Outcome:	The proposed evaluation metric outperforms existing methods on a CoNLL14 evaluation task.

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset (2024.lrec-main)

Copied to clipboard

Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang

Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation (2024.acl-long)

Challenge:	Existing studies have shown that visual information in existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities.
Approach:	They propose to use 3AM to create an ambiguity-aware multimodal machine translation dataset.
Outcome:	The proposed dataset includes more ambiguity and a greater variety of captions and images than other MMT datasets.

Copied to clipboard

Tengfei Yu, Xuebo Liu, Liang Ding, Kehai Chen, Dacheng Tao, Min Zhang

TasTe: Teaching Large Language Models to Translate through Self-Reflection (2024.acl-long)

Challenge:	End-to-end speech translation (ST) models require simultaneous crossmodal and crosslingual transformations to be effective.
Approach:	They propose a homophone-aware contrastive learning approach that integrates a speech-text masking strategy to reduce ambiguity.
Outcome:	The proposed approach achieves SOTA results on BLEU scores on different MuST-C and CoVoST ST tasks, underlining its effectiveness in reducing speech sense ambiguity.

Copied to clipboard

Yutong Wang, Jiali Zeng, Xuebo Liu, Fandong Meng, Jie Zhou, Min Zhang

TemplateGEC: Improving Grammatical Error Correction with Detection Template (2023.acl-long)

Challenge:	Existing approaches to enhance LLMs' performance in machine translation are unable to fully exploit their instruction-following capabilities.
Approach:	They propose a framework for translating through self-reflection that involves two stages of inference . they propose to use the framework to refine LLMs' preliminary translations .
Outcome:	The proposed framework can produce translation outputs that match the quality of NMT systems.

Copied to clipboard

Yinghao Li, Xuebo Liu, Shuo Wang, Peiyuan Gong, Derek F. Wong, Yang Gao, Heyan Huang, Min Zhang

Syntactic Text Processing

Challenge:	Existing methods for grammatical error correction (GEC) have been developed.
Approach:	They propose a method which integrates the detection labels from a Seq2Edit model to construct a template as the input.
Outcome:	The proposed method can perform human-in-the-loop error correction tasks.

Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix (2023.emnlp-main)

Copied to clipboard

Xinyu Ma, Xuebo Liu, Min Zhang

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments (2025.findings-emnlp)

Challenge:	Existing methods to cluster languages based on ancestral families can yield suboptimal results due to variations in the datasets employed during the model’s training phase.
Approach:	They propose a method that leverages the fisher information matrix to cluster language families anchored on the multilingual translation model's characteristics.
Outcome:	The proposed method improves performance over conventional language families in adapting a multilingual translation model to unfamiliar language pairs.

Copied to clipboard

Qingyu Lu, Liang Ding, Siyi Cao, Xuebo Liu, Kanjian Zhang, Jinxia Zhang, Dacheng Tao

AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs (2025.emnlp-main)

Challenge:	Experiments with 4 different LLMs across 5 embodied environments show significant efficiency improvements, with only minor drops in agent performance.
Approach:	They propose an intrinsic method that injects exit instructions during generation and an extransic system that verifies task completion to determine when to halt an agent’s trial.
Outcome:	The proposed method injects exit instructions during generation and an exit method verifies task completion to determine when to halt an agent’s trial.

Copied to clipboard

Xiaopeng Ke, Hexuan Deng, Xuebo Liu, Jun Rao, Zhenxi Song, Jun Yu, Min Zhang

Responsible & Trustworthy NLP

Challenge:	Existing approaches to synthesis large language models often suffer from performance limitations and high computational costs.
Approach:	They propose a framework for constructing instruction-tuning data from unlabeled data for any specialized domains from corresponding unlabed data.
Outcome:	The proposed framework is comparable to DeepSeek-V3 while utilizing just 17% of the production cost.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs (2025.findings-emnlp)

Copied to clipboard

Xiabin Zhou, Wenbin Wang, Minyan Zeng, Jiaxian Guo, Xuebo Liu, Li Shen, Min Zhang, Liang Ding

Challenge:	Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics, which hampers the effective retention of essential information while discarding less important tokens.
Approach:	They propose a Task-Aware KV cache mechanism that dynamically adjusts the KV caching size across different layers based on the characteristics of the tasks.
Outcome:	The proposed method surpasses state-of-the-art methods by 11% on the LongBench dataset even under extreme compression (0.9%)

Towards Making the Most of ChatGPT for Machine Translation (2023.findings-emnlp)

Copied to clipboard

Keqin Peng, Liang Ding, Qihuang Zhong, Li Shen, Xuebo Liu, Min Zhang, Yuanxin Ouyang, Dacheng Tao

Test-time Adaptation for Machine Translation Evaluation by Uncertainty Minimization (2023.acl-long)

Challenge:	Prior studies have shown that ChatGPT achieves comparable results to commercial systems for high-resource languages, but lags behind in complex tasks, e.g., low-resourced and distant-language-pairs translation.
Approach:	They propose task-specific prompts and domain-specific prompts which are based on task information and domain information and a task-specific prompt.
Outcome:	The proposed prompts improve the performance of ChatGPT in complex tasks and generate hallucinations for non-English-centric tasks.

Copied to clipboard

Runzhe Zhan, Xuebo Liu, Derek F. Wong, Cuilian Zhang, Lidia S. Chao, Min Zhang