Papers by Shujian Huang

Large Language Models are Limited in Out-of-Context Knowledge Reasoning (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown impressive language capabilities, but most of them have very unbalanced performance across different languages.
Approach:	They propose to use question translation data to enhance LLMs' multilingual capabilities by using mechanistic interpretability methods.
Outcome:	The proposed method improves multilingual alignment even with unannotated answers in English and a wide range of languages even with instruction-tuned LLMs.

Copied to clipboard

Peng Hu, Changjiang Gao, Ruiqi Gao, Jiajun Chen, Shujian Huang

IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) possess extensive knowledge and strong capabilities in performing in-context reasoning.
Approach:	They evaluated a dataset with seven representative OCKR tasks to assess their OCKr capabilities.
Outcome:	The model's OCKR abilities are limited regardless of whether the knowledge is trained in a separate or adjacent training setting.

Copied to clipboard

Xu Huang, Zhirui Zhang, Ruize Gao, Yichao Du, Lemao Liu, Guoping Huang, Shuming Shi, Jiajun Chen, Shujian Huang

Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge (2024.emnlp-main)

Challenge:	Existing systems that use a left-to-right completion paradigm are inefficient and expensive.
Approach:	They propose an open-source end-to-end interactive machine translation system platform . they propose to use a prefix-constrained decoding approach to achieve end- to-end evaluation .
Outcome:	The proposed system can guarantee high-quality, error-free translations . it uses prefix-constrained decoding and improves on previous systems .

Copied to clipboard

Jiahuan Li, Yiqing Cao, Shujian Huang, Jiajun Chen

Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention (N18-1)

Challenge:	Large language models have shown excellent performance on knowledge-intensive tasks, but pretraining data tends to contain misleading and conflicting information.
Approach:	They systematically analyze LLMs’ learning preferences for data with conflicting knowledge.
Outcome:	The proposed model outperforms human-level models on knowledge-intensive tasks by analyzing pretraining data.

Copied to clipboard

Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, Jiajun Chen

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction (2020.coling-main)

Challenge:	Neural machine translation models learn to map from source language sentences to target language sentences via continuous-space intermediate representations.
Approach:	They propose an encoder with character attention which augments the (sub)word-level representation with character-level information and a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively.
Outcome:	The proposed model outperforms the standard word-based model, subword-based models, and strong character-based ones on translation tasks.

Copied to clipboard

Yanyang Li, Yingfeng Luo, Ye Lin, Quan Du, Huizhen Wang, Shujian Huang, Tong Xiao, Jingbo Zhu

What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation (2023.findings-acl)

Challenge:	Recent work has questioned the robustness of unsupervised bilingual dictionary induction methods on distant language pairs.
Approach:	They propose an iterative dimension reduction method to bridge this gap . they propose a method that initializes and self-learning and inducing a dictionary .
Outcome:	The proposed method achieves 13.64 55.53% accuracy between English and four distant languages.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Yunzhe Lv, Xin Zheng, Jiajun Chen

Explicit Semantic Decomposition for Definition Generation (2020.acl-main)

Challenge:	kNN-MT builds an external datastore, which saves all target language token occurrences in the parallel corpus.
Approach:	They propose a new paradigm for domain adaptation by building an external datastore which usually saves all target language token occurrences in the parallel corpus.
Outcome:	The proposed model can be easily pruned according to local correctness, and it is more explainable.

Copied to clipboard

Jiahuan Li, Yu Bao, Shujian Huang, Xinyu Dai, Jiajun Chen

Challenge:	Existing definition generation methods rely on decoding to extract semantic components of words.
Approach:	They propose a method which explicitly decomposes meaning of words into semantic components and models them with discrete latent variables for definition generation.
Outcome:	The proposed method outperforms existing methods on WordNet and Oxford benchmarks.

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Copied to clipboard

Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach:	They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome:	Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.

Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)

Copied to clipboard

Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xin-yu Dai, Jiajun Chen

Syntactic Text Processing

Challenge:	Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space.
Approach:	They propose to generate sentences from disentangled syntactic and semantic spaces by using the linearized tree sequence.
Outcome:	The proposed method achieves similar or better performance in various tasks compared with state-of-the-art models.

Learning from Adjective-Noun Pairs: A Knowledge-enhanced Framework for Target-Oriented Multimodal Sentiment Classification (2022.coling-1)

Copied to clipboard

Fei Zhao, Zhen Wu, Siyu Long, Xinyu Dai, Shujian Huang, Jiajun Chen

Multimodality

Challenge:	Existing methods to determine sentiment polarity of opinion target are inconsistent and lack visual attention.
Approach:	They propose a framework which can exploit adjective-noun pairs extracted from images to improve visual attention and sentiment prediction capability of the TMSC task.
Outcome:	The proposed framework outperforms state-of-the-art on two public datasets.

Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation (D19-1)

Copied to clipboard

Huiyun Yang, Shujian Huang, Xin-Yu Dai, Jiajun Chen

Alleviating the Inequality of Attention Heads for Neural Machine Translation (2022.coling-1)

Challenge:	Existing domain adaptation methods focus on the adaptation from the source domain to the entire target domain without considering the diversity of individual sample samples.
Approach:	They propose a fine-grained knowledge fusion model with the domain relevance modeling scheme to control the balance between learning from the target domain data and learning from a source domain model.
Outcome:	The proposed model outperforms baselines and state-of-the-art models on three sequence labeling tasks.

Copied to clipboard

Zewei Sun, Shujian Huang, Xinyu Dai, Jiajun Chen

Adaptive Nearest Neighbor Machine Translation (2021.acl-short)

Challenge:	Recent studies show that the attention heads in Transformer are not equal.
Approach:	They propose a masking method to mask attention heads in Transformer . they empirically validate the inequality and propose 'head mask' method to avoid bottleneck .
Outcome:	The proposed masking method improves translation performance on multiple languages . it can be used to remove a small subset of heads without affecting performance .

Copied to clipboard

Xin Zheng, Zhirui Zhang, Junliang Guo, Shujian Huang, Boxing Chen, Weihua Luo, Jiajun Chen

MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization (2024.acl-long)

Challenge:	kNN-MT uses pre-trained NMT model with token-level k-nearest-neighbor retrieval to improve translation accuracy.
Approach:	They propose a method that combines a pre-trained NMT model with token-level k-nearest-neighbor retrieval to improve translation accuracy.
Outcome:	The proposed method outperforms the existing model on four benchmark datasets and is open-source.

Copied to clipboard

Shuaijie She, Wei Zou, Shujian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation (2022.acl-long)

Challenge:	Existing models exhibit inconsistent reasoning abilities across different languages . existing models lack consistency across languages due to imbalance of training data .
Approach:	They propose a multilingual alignment-as-preference optimization framework to align reasoning processes in other languages with the dominant language.
Outcome:	The proposed framework improves multilingual reasoning across languages on three benchmarks.

Copied to clipboard

Yanling Xiao, Lemao Liu, Guoping Huang, Qu Cui, Shujian Huang, Shuming Shi, Jiajun Chen

Structure-Unified M-Tree Coding Solver for Math Word Problem (2022.emnlp-main)

Challenge:	Existing IMT systems relying on lexical constrained decoding (LCD) are limited in translation efficiency and quality due to LCD.
Approach:	They propose a novel interactive neural machine translation system that uses lexical constraints to decode missing words in a manually revised translation.
Outcome:	The proposed system performs significantly better and faster than state-of-the-art IMT on three translation tasks.

Copied to clipboard

Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, Shujian Huang, Jiajun Chen

Numerical Reasoning

Challenge:	Existing models that take into account the binary tree structure of mathematical expressions have achieved better performance, but the output space is non-deterministic.
Approach:	They propose a Structure-Unified M-Tree Coding Solver which applies a tree with any M branches to unify the output structures.
Outcome:	The proposed model outperforms several state-of-the-art models under similar experimental conditions and performs much better under low-resource conditions.

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)

Copied to clipboard

Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

MultiSQL: A Schema-Integrated Context-Dependent Text2SQL Dataset with Diverse SQL Operations (2024.findings-acl)

Challenge:	Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
Approach:	They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants.
Outcome:	The proposed approach improves performance across benchmarks and representation space.

Copied to clipboard

Chunhui Li, Yifan Wang, Zhen Wu, Zhen Yu, Fei Zhao, Shujian Huang, Xinyu Dai

Natural Language Interfaces

Challenge:	Text2SQL is a task that translates natural language into SQL statements.
Approach:	They propose a task that translates natural language into SQL statements.
Outcome:	The proposed task enables users to convert natural language into SQL statements.

PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment (2024.emnlp-main)

Copied to clipboard

Jiahuan Li, Shujian Huang, Aarron Ching, Xinyu Dai, Jiajun Chen

A Reinforced Generation of Adversarial Examples for Neural Machine Translation (2020.acl-main)

Challenge:	Large language models exhibit reasonable multilingual abilities, despite predominantly English-centric pretraining.
Approach:	They propose a framework that establishes multilingual alignment prior to language model pretraining and preserves this alignment using a code-switching strategy during pretraining.
Outcome:	Experiments in a synthetic English to English-Clone setting show that PreAlign outperforms standard multilingual joint training in language modeling, zero-shot cross-lingual transfer, and cross-linguistic knowledge application.

Copied to clipboard

Wei Zou, Shujian Huang, Jun Xie, Xinyu Dai, Jiajun Chen

Robustness in NLP

Challenge:	Neural machine translation systems fail on less decent inputs, which may harm the credibility of these systems.
Approach:	They propose a paradigm that generates adversarial examples using reinforcement learning to expose pitfalls for a given performance metric.
Outcome:	The proposed paradigm produces stable attacks with meaning-preserving adversarial examples.

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation (2024.findings-acl)

Copied to clipboard

Xu Huang, Zhirui Zhang, Xiang Geng, Yichao Du, Jiajun Chen, Shujian Huang

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)

Challenge:	Recent studies have shown that Large Language Models (LLMs) can be used as translation evaluators.
Approach:	They propose to use both coarse-grained and fine-grounded prompts to discern the utility of source versus reference data in machine translation evaluation tasks.
Outcome:	The proposed model can be used to evaluate translations in multiple languages.

Copied to clipboard

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

Analyzing the Intensity of Complaints on Social Media (2022.findings-naacl)

Challenge:	Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs.
Approach:	They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents.
Outcome:	The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China .

Copied to clipboard

Ming Fang, Shi Zong, Jing Li, Xinyu Dai, Shujian Huang, Jiajun Chen

Cross-Lingual Transfer

Challenge:	Prior studies on identifying the existence or the type of complaints focus on building automatic classification models for identifying complaints.
Approach:	They propose to measure the intensity of complaints from text using Best-Worst Scaling method to estimate the popularity of posts on social media.
Outcome:	The proposed model can estimate the popularity of complaints on social media with best-worst scaling (BWS) method.

Dynamic Past and Future for Neural Machine Translation (D19-1)

Copied to clipboard

Zaixiang Zheng, Shujian Huang, Zhaopeng Tu, Xin-Yu Dai, Jiajun Chen

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Challenge:	Neural machine translation models can benefit from modeling translated and untranslated source contents as recurrent states, but this less interpretable recurrence hinders their power to model dynamic updating of and contents during decoding.
Approach:	They propose to model the dynamic updating of and contents during decoding by explicitly separating source words into groups of translated and untranslated contents through parts-to-wholes assignment.
Outcome:	The proposed method achieves significant improvements over both Rnmt and Transformer by producing more adequate translations.

Copied to clipboard

Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu

Rethinking Document-level Neural Machine Translation (2022.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach:	They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome:	The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.

Copied to clipboard

Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Shujian Huang, Jiajun Chen, Lei Li

Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)

Challenge:	Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence .
Approach:	They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly .
Outcome:	The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages.

Copied to clipboard

Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang

Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping (2024.findings-emnlp)

Challenge:	evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT).
Approach:	They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations .
Outcome:	The proposed model outperforms strong baselines in both supervised and unsupervised settings.

Copied to clipboard

Wenhao Zhu, Sizhe Liu, Shujian Huang, Shuaijie She, Chris Wendler, Jiajun Chen

FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation (2022.lrec-1)

Challenge:	Decoding by contrasting layers (DoLa) is designed to improve the generation quality of large language models (LLMs) however, this approach does not work well on non-English tasks.
Approach:	They propose a contrastive decoding algorithm that uses amateur logits to contrast with the output of an expert model's early exit logits.
Outcome:	The proposed method outperforms baselines and significantly improves chain-of-thought reasoning accuracy across 11 languages.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Tong Pu, Pingxuan Huang, Xu Zhang, Jian Yu, Wei Chen, Yanfeng Wang, Jiajun Chen

Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models (2024.acl-long)

Challenge:	Recent research on domain adaptation neglects diversity in translation within a domain . current research on NMT models considers very broad target domains .
Approach:	They propose a fine-grained domain adaptation task for autonomous vehicles, AI education, real-time networks, and smart phone.
Outcome:	The proposed task is compared with a dataset of Chinese-English translation tasks for four sub-domains of information technology: autonomous vehicles, AI education, real-time networks, and smart phone.

Copied to clipboard

Changjiang Gao, Jixing Li, Jiajun Chen, Shujian Huang

Exploiting Noisy Data in Distant Supervision Relation Classification (N19-1)

Challenge:	Existing computational metric to quantify extent of meaning composition is lacking . despite extensive neurolinguistic research, understanding how meaning is constructed is difficult .
Approach:	They propose a computational metric to quantify the degree of meaning composition . they use key-value memory interpretation of transformer feed-forward network blocks to study meaning composition.
Outcome:	Experimental results show that the metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting multifaceted nature of meaning composition during human sentence comprehension.

Copied to clipboard

Kaijia Yang, Liang He, Xin-yu Dai, Shujian Huang, Jiajun Chen

Text Classification

Challenge:	Existing approaches to relation classification are noisy and time-consuming . RCEND uses noisy data to split noisy data into correctly and incorrectly labeled data .
Approach:	They propose a framework to enhance relation classification by exploiting noisy data . they use an instance discriminator with reinforcement learning to split noisy data into correctly and incorrectly labeled data based on the noisy data.
Outcome:	The proposed method outperforms the state-of-the-art models on relation classification . the proposed method is based on a semi-supervised learning method .

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement (2025.findings-acl)

Copied to clipboard

Peng Ding, Jun Kuang, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks but are vulnerable to meticulously crafted jailbreak attacks.
Approach:	They propose a training-free defense strategy to align LLMs’ strong safety discrimination performance with their relatively weaker safety generation ability.
Outcome:	The proposed strategy achieves an average 99% success rate against numerous complex and covert jailbreak methods while maintaining helpfulness on general benchmarks.

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation (2026.findings-acl)

Copied to clipboard

Renfei Dang, Peng Hu, Zhejian Lai, Changjiang Gao, Min Zhang, Shujian Huang

Self-Evolution Knowledge Distillation for LLM-based Machine Translation (2025.coling-main)

Challenge:	Prior studies have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information.
Approach:	They propose to conduct a fine-grained analysis of large language models using a dataset Biography-Reasoning and QA and knowledge reasoning tasks to understand their findings.
Outcome:	The proposed model is able to perform a range of downstream tasks without requiring a large amount of knowledge and is compared with a control dataset.

Copied to clipboard

Yuncheng Song, Liang Ding, Changtong Zan, Shujian Huang

kNN-BOX: A Unified Framework for Nearest Neighbor Generation (2024.eacl-demo)

Challenge:	Existing knowledge distillation strategies for large language models minimize output distributions between student and teacher models indiscriminately for each token.
Approach:	They propose a distillation strategy that integrates teacher and one-hot distribution of ground truth into the student distribution as prior knowledge, which promotes the distillation process.
Outcome:	The proposed method brings an average improvement of approximately 1.4 SacreBLEU points across four translation directions in the WMT22 test sets.

Copied to clipboard

Wenhao Zhu, Qianfeng Zhao, Yunzhe Lv, Shujian Huang, Siheng Zhao, Sizhe Liu, Jiajun Chen

Large Language Models Are Cross-Lingual Knowledge-Free Reasoners (2025.naacl-long)

Challenge:	kNN-BOX enables quick development and visualization for novel generation paradigm . Currently, knn-BOx has provided implementation of seven popular kN-MT variants .
Approach:	They propose a framework which decomposes the datastore-augmentation approach into three modules . they apply kNN-BOX to machine translation and three other tasks .
Outcome:	The proposed framework decomposes the datastore-augmentation approach into three modules . it provides implementation of seven popular kNN-MT variants, covering research from performance enhancement to efficiency optimization.

Copied to clipboard

Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering (2024.emnlp-main)

Challenge:	Large language models have demonstrated impressive reasoning capabilities across multiple languages, but the relationship between capabilities in different languages is less explored.
Approach:	They decompose the process of reasoning tasks into two separate components: knowledge retrieval and knowledge-free reasoning.
Outcome:	The proposed model can be transferred across source-target languages despite secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer.

Copied to clipboard

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

Natural Language Interfaces

Challenge:	Existing retrieval-augmented generation methods rely on multiple calls of large language models (LLMs) Large-language models lack knowledge underrepresented in training data and still face hallucinations.
Approach:	They propose an efficient retriever for multi-hop question answering that generates new queries iteratively without the need for LLM calls.
Outcome:	The proposed method surpasses existing methods on three open-domain multi-hop question-answering datasets.

Local Interpretation of Transformer Based on Linear Decomposition (2023.acl-long)

Copied to clipboard

Sen Yang, Shujian Huang, Wei Zou, Jianbing Zhang, Xinyu Dai, Jiajun Chen

Explainability & Interpretability in NLP

Challenge:	Existing work on local explanation generation attempts to understand model dynamics on word-level or phraselevel by assigning importance scores on input features.
Approach:	They propose to interpret neural networks by linear decomposition by a Transformer model on a single input and a linear decomposing of the output to generate local explanations.
Outcome:	The proposed method achieves competitive performance in sentiment classification and machine translation, and fidelity of explanation.

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)

Copied to clipboard

Xin Chen, Feng Jiang, Yiqian Zhang, Hardy Chen, Shuo Yan, Wenya Xie, Min Yang, Shujian Huang

R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)

Challenge:	Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions .
Approach:	They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification.
Outcome:	The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing.

Copied to clipboard

Shuaijie She, Junxiao Liu, Yifeng Liu, Jiajun Chen, Xin Huang, Shujian Huang

Non-Autoregressive Translation by Learning Target Categorical Codes (2021.naacl-main)

Challenge:	Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.
Approach:	They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation.
Outcome:	The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores.

Copied to clipboard

Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen

INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation (2023.acl-long)

Challenge:	Existing non-autoregressive text generation models still fall behind in translation quality . authors propose a model that learns implicitly categorical codes as latent variables .
Approach:	They propose a non-autoregressive Transformer model that implicitly categorizes latent variables into decoding . they find it improves translation quality by introducing more informative decoder inputs .
Outcome:	The proposed model achieves comparable or better performance in machine translation tasks than strong baselines.

Copied to clipboard

Wenhao Zhu, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Neural machine translation models induce a non-smooth representation space, which harms its generalization results.
Approach:	They propose a framework to smooth the representation space by adjusting neighbor representations with a small number of new parameters.
Outcome:	The proposed framework outperforms the state-of-the-art kNN-MT system with average gains of 1.99 COMET and 1.0 BLEU on four benchmark datasets.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly (2024.naacl-long)

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

Copied to clipboard

Changjiang Gao, Hongda Hu, Peng Hu, Jiajun Chen, Jixing Li, Shujian Huang

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)

Challenge:	Current large language models show imbalance abilities in different languages . authors propose two approaches to improve cross-lingual knowledge alignment .
Approach:	They propose a framework to assess cross-lingual knowledge alignment of large language models . they propose multilingual pretraining and multilingual instruction tuning to address this problem .
Outcome:	The proposed framework assesses the cross-lingual knowledge alignment of LLMs in performance, consistency and conductivity levels.

Copied to clipboard

Peng Ding, Wen Sun, Dailin Li, Wei Zou, Jiaming Wang, Jiajun Chen, Shujian Huang

Online Distilling from Checkpoints for Neural Machine Translation (N19-1)

Challenge:	Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation.
Approach:	They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement.
Outcome:	The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase.

Copied to clipboard

Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, Jiajun Chen

Addressing Linguistic Bias through a Contrastive Analysis of Academic Writing in the NLP Domain (2023.emnlp-main)

Challenge:	Existing neural machine translation models have a deep structure with large amounts of parameters, making them hard to train.
Approach:	They propose an online method to generate a teacher model from checkpoints . they show steady improvement over a strong self-attention-based baseline system .
Outcome:	The proposed method improves on-the-fly on several datasets and language pairs.

Copied to clipboard

Robert Ridley, Zhen Wu, Jianbing Zhang, Shujian Huang, Xinyu Dai

Question Translation Training for Better Multilingual Reasoning (2024.findings-acl)

Challenge:	a reviewer’s opinion of the nativeness of expression in an academic paper affects the likelihood of it being accepted for publication.
Approach:	They conduct a statistical analysis of paper abstracts from the natural language processing domain to identify how authors from different linguistic backgrounds differ in the lexical, morphological, syntactic and cohesive aspects of their writing.
Outcome:	The results suggest that there is potential for linguistic bias in the domain of natural language processing.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch

Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention (2023.findings-emnlp)

Challenge:	Large language models have shown compelling performance on reasoning tasks but they tend to perform much worse in languages other than English.
Approach:	They propose to train a model to translate reasoning questions into English by fine tuning on X-English parallel question data.
Outcome:	The proposed approach improves on LLaMA2-13B on the MGSM and MSVAMP multilingual reasoning benchmarks.

Copied to clipboard

Changjiang Gao, Shujian Huang, Jixing Li, Jiajun Chen

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective (2022.findings-emnlp)

Challenge:	Recent large language models (LLMs) have shown strong abilities to understand natural language, but how these factors affect the models’ language perception is unclear.
Approach:	They compare the self-attention of several existing large language models in different sizes to assess the effect of scaling and instruction tuning on language perception.
Outcome:	The proposed models are closer to non-native speakers than native speakers in attention, suggesting a sub-optimal language perception of all models.

Copied to clipboard

Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

Multimodality

Challenge:	In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
Approach:	They propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models.
Outcome:	The proposed method analyzes captions generated by five popular VLP models to reveal how well they align with visual words and how well these align with images.

RPD: A Distance Function Between Word Embeddings (2020.acl-srw)

Copied to clipboard

Xuhui Zhou, Shujian Huang, Zaixiang Zheng

Representation Learning

Challenge:	Existing word embeddings are poorly understood, but little is known about how they differ between different sets of word embeds.
Approach:	They propose a metric called Relative Pairwise Inner Product Distance to quantify the distance between different word embeddings.
Outcome:	The proposed metric measures the distance between different sets of embeddings and investigates the influence of different training processes and corpora.

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Yunzhi Shen, Hao Zhou, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation (2025.emnlp-main)

Challenge:	Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization.
Approach:	They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.
Outcome:	The proposed framework supports global exploration and fine-grained optimization while supporting global exploration.

Copied to clipboard

Sen Yang, Yu Bao, Yu Lu, Jiajun Chen, Shujian Huang, Shanbo Cheng

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification (2021.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation.
Approach:	They propose a synthetic data generation framework that leverages models’ established English-to-x (en2x) capabilities by extending English parallel corpora into omnidirectional datasets and developing an English-referenced quality evaluation proxy.
Outcome:	The proposed framework achieves significant improvement across 72 x2x directions while generalizing to enhance en2x performance.

Copied to clipboard

Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, Shujian Huang, Jiajun Chen

TRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data (2025.findings-acl)

Challenge:	Large-scale multi-label text classification tasks often face long-tailed label distributions, where many labels have few or even no training instances.
Approach:	They propose a meta-learning approach that incorporates the objective of adapting to new low-resource tasks into the meta-Learning phase.
Outcome:	The proposed approach achieves state-of-the-art against strong baselines and can still enhance powerful BERTlike models.

Copied to clipboard

Wei Zou, Sen Yang, Yu Bao, Shujian Huang, Jiajun Chen, Shanbo Cheng

latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (2022.acl-long)

Challenge:	Large Language Models (LLMs) have reshaped machine translation, but multilingual MT still relies heavily on parallel data for supervised fine-tuning.
Approach:	They propose a framework that leverages only monolingual data and the intrinsic multilingual knowledge of Large Language Models (LLMs).
Outcome:	The proposed framework matches models trained on large-scale parallel data and excels in non-English translation directions.

Copied to clipboard

Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei Li

Multimodality

Challenge:	Recent advances in text generation have limited applications due to multimodality problem.
Approach:	They propose a method which uses latent variables to capture word categorical information and invoke an advanced curriculum learning technique to overcome multi-modality problem.
Outcome:	The proposed method outperforms strong baselines without an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm.

A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily (2024.naacl-long)

Copied to clipboard

Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, Shujian Huang

When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation (2021.acl-short)

Challenge:	Existing methods for generating 'jailbreaks' suffer from manual design or require optimization on other white-box models, which compromises either generalization or efficiency.
Approach:	They propose a framework that leverages LLMs to generate effective jailbreak prompts and a generalized framework that can be used to generate prompts.
Outcome:	The proposed framework improves the attack success rate while reducing the time cost compared to baselines.

Copied to clipboard

Jiahuan Li, Yutong Shen, Shujian Huang, Xinyu Dai, Jiajun Chen

MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation (2024.naacl-long)

Challenge:	Subword segmentation algorithms can produce sub-optimal segmentation when the target language is rich in morphological changes or there is not enough data for learning compact composition rules.
Approach:	They compare character-based and subword-based neural machine translation systems . they find character-driven models are better at handling morphological phenomena .
Outcome:	The character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.

Copied to clipboard

Jiahuan Li, Shanbo Cheng, Shujian Huang, Jiajun Chen

Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown their strong ability in the field of machine translation, yet they suffer from high computational cost and latency.
Approach:	They propose a framework which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner.
Outcome:	The proposed framework transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner.

Copied to clipboard

Xinyou Wang, Zaixiang Zheng, Shujian Huang

Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling (N19-1)

Challenge:	Non-autoregressive (NAR) neural machine translation models require a conditional independence assumption on target sequences, resulting in less informative learning signals.
Approach:	They propose a model-agnostic multi-task learning framework to provide more informative learning signals for NAR models under conventional MLE training.
Outcome:	The proposed framework improves accuracy of multiple NAR baselines without additional decoding overhead.

Copied to clipboard

Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang, Jiajun Chen

Sentiment Analysis

Challenge:	Opinion target extraction and opinion words extraction are two fundamental subtasks in Aspect Based Sentiment Analysis (ABSA).
Approach:	They propose a new subtask for Aspect Based Sentiment Analysis to extract opinion words as pairs from a given opinion target.
Outcome:	The proposed model outperforms existing methods significantly on several popular ABSA benchmarks.

Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From (2025.emnlp-main)

Copied to clipboard

Changjiang Gao, Hankun Lin, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Jiajun Chen, Shujian Huang

Cross-Lingual Transfer

Challenge:	Cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment, but the performance and mechanism of it for large language models (LLMs) remains unclear.
Approach:	They evaluate cross-lingual context retrieval of over 40 large language models . they use cross-linguistic machine reading comprehension as a representative scenario .
Outcome:	The results show that open LLMs show strong cross-lingual context retrieval ability . the results also show that their oracle performances improve after training .

Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models (2024.naacl-long)

Copied to clipboard

Shuaijie She, Shujian Huang, Xingyun Wang, Yanke Zhou, Jiajun Chen

Natural Language Interfaces

Challenge:	LLMs generate responses following user's instructions, which requires high dialogue comprehension ability.
Approach:	They propose to evaluate LLMs' dialogue comprehension ability using a dialogue summarization task to derive factual questions from the generated summaries and use them as a more flexible measurement of dialogue comprehension.
Outcome:	The proposed model reduces the error rate by 11% on the dialogue summarization task.

Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering (P19-1)

Copied to clipboard

Peng Wu, Shujian Huang, Rongxiang Weng, Zaixiang Zheng, Jianbing Zhang, Xiaohui Yan, Jiajun Chen

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to detect relation detection only get high accuracy for questions whose relations have been seen in training data.
Approach:	They propose a method to learn representation mapping for both seen and unseen relations based on previously learned relation embedding.
Outcome:	The proposed method improves the performance of unseen relations while keeping the performance comparable to the state-of-the-art.

Copied to clipboard

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan

Dialogue State Tracking with Explicit Slot Connection Modeling (2020.acl-main)

Challenge:	Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach:	They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome:	Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.

Copied to clipboard

Yawen Ouyang, Moxin Chen, Xinyu Dai, Yinggong Zhao, Shujian Huang, Jiajun Chen

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to track dialogue state are lacking in multi-domain scenarios.
Approach:	They propose a model that explicitly considers slot correlations across domains . they propose ellipsis and reference to express values that have been mentioned by slots from other domains.
Outcome:	The proposed model outperforms existing models on multi-domain datasets and achieves state-of-the-art performance.

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training (2023.acl-long)

Copied to clipboard

Yiming Yan, Tao Wang, Chengqi Zhao, Shujian Huang, Jiajun Chen, Mingxuan Wang

Process-based Self-Rewarding Language Models (2025.findings-acl)

Challenge:	Automated metrics are used for machine translation, but they are often considered to be black boxes with potential biases that are difficult to detect.
Approach:	They analyze automatic metrics from the perspective of their guidance for machine translation training.
Outcome:	The proposed measures improve the performance of machine translation models.

Copied to clipboard

Shimao Zhang, Xiao Liu, Xin Zhang, Junxiao Liu, Zheheng Luo, Shujian Huang, Yeyun Gong

Improving Long-Context Translation via Self-Supervised Dual Learning (2026.acl-long)

Challenge:	Existing methods to reward LLMs' outputs are not effective in mathematical reasoning scenarios and may lead to a decline in performance.
Approach:	They propose a process-based self-rewarding pipeline that integrates long-thought reasoning, step-wise LLM-as-a-Judge, and step- wise preference optimization within the existing paradigm.
Outcome:	The proposed model improves the performance of Large Language Models on multiple mathematical reasoning benchmarks and shows that it can surpass human capabilities.

Copied to clipboard

Shanbo Cheng, Shuaijie She, Yu Bao, Jianbing Zhang, Jiajun Chen, Shujian Huang

Energy-based Unknown Intent Detection with Data Manipulation (2021.findings-acl)

Challenge:	Large language models with long context windows suffer from catastrophic information distortion, undermining the strict faithfulness required for translation.
Approach:	They propose a self-supervised post-training framework that improves long-document translation reliability via round-trip consistency.
Outcome:	The proposed framework improves long-document translation reliability via round-trip consistency.

Copied to clipboard

Yawen Ouyang, Jiasheng Ye, Yu Chen, Xinyu Dai, Shujian Huang, Jiajun Chen

Sentiment Analysis

Challenge:	Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose intent has never appeared in the training set.
Approach:	They propose a framework to generate high-quality OOD utterances with importance weighTs (GOT) their framework is fine-tuned to detect out-of-distribution utterrances .
Outcome:	The proposed framework can achieve state-of-the-art results on two benchmark datasets.

Learning Kernel-Smoothed Machine Translation with Retrieved Examples (2021.emnlp-main)

Copied to clipboard

Qingnan Jiang, Mingxuan Wang, Jun Cao, Shanbo Cheng, Shujian Huang, Lei Li

Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation (2025.acl-long)

Challenge:	Existing methods to update deployed models are prone to overfit . however, non-parametric methods are liable to over-fit the retrieved examples .
Approach:	They propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER) this approach allows users to adapt models to emerging cases without retraining .
Outcome:	The proposed approach achieves 1.1 to 1.5 BLEU scores over existing methods without retraining . the proposed model is released on https://github.com/jiangqn/KSTER.

Copied to clipboard

Xiang Geng, Zhejian Lai, Jiajun Chen, Hao Yang, Shujian Huang

Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation (2021.findings-emnlp)

Challenge:	Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task.
Approach:	They propose a framework for alleviating distribution shift in synthetic QE data . they employ a constrained beam search algorithm and distinct generation models to enhance translation diversity.
Outcome:	The proposed framework outperforms SOTA baselines like CometKiwi in supervised and unsupervised settings.

Copied to clipboard

Xin Zheng, Zhirui Zhang, Shujian Huang, Boxing Chen, Jun Xie, Weihua Luo, Jiajun Chen

Unsupervised Bilingual Lexicon Induction via Latent Variable Models (D18-1)

Challenge:	kNN-MT is a non-parametric method that uses nearest neighbor retrieval to translate out-of-domain sentences, rare words, etc.
Approach:	They propose a framework that directly uses in-domain monolingual sentences to build an effective datastore for k-nearest-neighbor retrieval.
Outcome:	The proposed framework improves translation accuracy with target-side monolingual data while achieving comparable performance with back-translation.

Copied to clipboard

Zi-Yi Dou, Zhi-Hao Zhou, Shujian Huang