Papers by Xin Deng

Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Challenge:	Existing models rely on pre-trained language models, which have a maximum input sequence length of 512 tokens, and therefore have 'input length limitation'.
Approach:	They propose a text segmentation algorithm which guarantees to produce the optimal segmentation to address the issue of input length limitation caused by PLMs.
Outcome:	The proposed method improves both text and label representations on MLTC datasets, unraveling the intricate correlations between texts and labels.

Copied to clipboard

Multilinguality

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.

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction (2022.findings-acl)

Copied to clipboard

Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, ShiLiang Zhang, Bing Li, Wei Wang, Xin Cao

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Challenge:	Keyphrase extraction (KPE) extracts phrases in a document that provide a concise summary of the core content.
Approach:	They propose an unsupervised keyphrase extraction method that ranks candidates by similarity between embeddings of source document and masked document.
Outcome:	The proposed method outperforms state-of-the-art methods on six benchmarks . it achieves average 3.53 improvement over the existing method .

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

SpecEdit: A Spectral Approach for Multi-Round Knowledge Editing (2026.findings-acl)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Junxian Liu, Zikun Deng, Xin Wu, Dazhen Deng, Yi Cai

Explainability & Interpretability in NLP

Challenge:	Multi-round knowledge editing suffers from performance degradation as edits accumulate . intrinsic knowledge of model and historical edit memories are naively coupled during editing . SpecEdit improves model editing performance by reducing destructive coupling .
Approach:	They propose a spectral-based model editing module that integrates into existing editing methods without altering their original optimization procedures.
Outcome:	The proposed model improves performance on multiple LLMs and editing methods.

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents (2024.acl-long)

Copied to clipboard

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning (2025.findings-emnlp)

Challenge:	Current language model-driven agents lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Approach:	They propose a benchmark to inspect users’ implicit intentions through explicit queries and a model expert as the upstream in agent design to enhance user-agent interaction.
Outcome:	The proposed approach excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

Copied to clipboard

Mengyi Deng, Xin Li, Tingyu Zhu, Zhicheng Yang, Zhijiang Guo, Wei Wang

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)

Challenge:	Existing methods for o1-level performance focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning patterns.
Approach:	They construct a reverse reasoning dataset and examine how it is supervised . they find that naively mixing forward and reverse data during SFT weakens the directional distinction .
Outcome:	The proposed model improves accuracy by 1.6%–6.8% over a standard model.

Copied to clipboard

Jia Deng, Junyi Li, Xin Zhao, Jinpeng Wang, Hongyu Lu, Ji-Rong Wen

Aspect-based Sentiment Analysis in Question Answering Forums (2021.findings-emnlp)

Challenge:	Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies.
Approach:	They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies.
Outcome:	The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks.

Copied to clipboard

Wenxuan Zhang, Yang Deng, Xin Li, Lidong Bing, Wai Lam

Sentiment Analysis

Challenge:	Existing studies on aspects-based sentiment analysis focus on a single opinionated sentence.
Approach:	They propose a model to combine aspects and their sentiments for QA forums . they use cross-sentence aspect-opinion interaction modeling to align the aspect mentioned in the question and associated opinion clues in the answer.
Outcome:	The proposed model outperforms baseline models on three real-world datasets.

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Yulan Yuan, Zhijiang Guo, Wei Wang

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

Challenge:	Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach:	They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome:	The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.

Copied to clipboard

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

Multilinguality

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.

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs (2026.acl-long)

Copied to clipboard

Yitian Gong, Luozhijie Jin, Kuangwei Chen, Dong Zhang, Ruifan Deng, Xiaogui Yang, Xin Zhang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu

Multimodality

Challenge:	Existing speech codecs struggle to balance these objectives at low bitrates . XY-Tokenizer achieves stronger semantic alignment than representative semantic-distillation codec .
Approach:	They propose a low-bitrate speech codec that aligns discrete speech representations with text while preserving fine-grained acoustic details for reconstruction.
Outcome:	The proposed codec outperforms existing low-bitrate speech codecs in speech understanding and generation tasks.

NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding (2024.findings-emnlp)

Copied to clipboard

Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song

GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)

Challenge:	Theory of mind evaluations currently focus on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations.
Approach:	They propose a benchmark to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states.
Outcome:	The proposed benchmark builds upon the Belief-Desire-Intention theory and conducts the necessary empirical experiments to evaluate large language models.

Copied to clipboard

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves.
Approach:	They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level .
Outcome:	The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

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

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

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

NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.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

Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin

Machine Translation

Challenge:	Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment.
Approach:	They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning .
Outcome:	The proposed method outperforms baseline models on NL-to-Lean 4 tasks.

Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)

Copied to clipboard

Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang

Multimodality

Challenge:	Existing methods for retrieving historical messages are based on similarity-based mechanisms.
Approach:	They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection.
Outcome:	The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S.

Fast Quiet-STaR: Thinking Without Thought Tokens (2025.findings-emnlp)

Copied to clipboard

Wei Huang, Yizhe Xiong, Xin Ye, Zhijie Deng, Hui Chen, Zijia Lin, Guiguang Ding

UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Challenge:	Large Language Models have achieved impressive performance across a range of tasks, but further gains require more than scaling up model sizes or training data.
Approach:	They propose a method that gradually reduces the number of thought tokens . this method allows models to internalize more abstract reasoning processes .
Outcome:	The proposed framework preserves the benefits of token-level reasoning while reducing computational cost.

Copied to clipboard

Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs (2025.findings-acl)

Challenge:	Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach:	They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome:	The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.

Copied to clipboard

Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu

Challenge:	Positional biases in large language models hinder their ability to process long inputs.
Approach:	They propose a benchmark to assess positional bias in large language models involving multiple pieces of relevant information.
Outcome:	The proposed benchmark assesses the performance of long-context language models by examining their models with different input lengths and tasks.

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)

Copied to clipboard

Zijie Dai, Shiyuan Deng, Sheng Guan, Yizhou Tian, Xin Yao, Xiao Yan, James Cheng

Green & Sustainable NLP

Challenge:	Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption.
Approach:	They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.
Outcome:	Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation (2022.emnlp-main)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Deng Cai, Xin Li, Jackie Chun-Sing Ho, Lidong Bing, Wai Lam

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Challenge:	Existing studies on multilingual sentence embeddings focus on cross-lingual semantic textual similarity and transfer tasks.
Approach:	They propose a method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR) . they compare existing multi-lingual sentence embedded with AMR and improve their versions by reducing the surface variations across different languages and expressions.
Outcome:	The proposed method improves state-of-the-art multilingual sentence embeddings on transfer tasks and semantic textual similarity tests.

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

LCQMC:A Large-scale Chinese Question Matching Corpus (C18-1)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Xin Liu, Qingcai Chen, Chong Deng, Huajun Zeng, Jing Chen, Dongfang Li, Buzhou Tang

Paraphrasing

Challenge:	Existing methods for question answering system lack large-scale question matching corpora . lack of large-sized question matching results in problem solving .
Approach:	They propose a large-scale Chinese question matching corpus which is released to the public . they use a search engine to collect large-sized question pairs related to high-frequency words .
Outcome:	The proposed corpus is more general than paraphrase corpus as it focuses on intent matching rather than paraphrasing.

Towards Generative Aspect-Based Sentiment Analysis (2021.acl-short)

Copied to clipboard

Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, Wai Lam

Sentiment Analysis

Challenge:	Existing work on Aspect-based sentiment analysis ignores the rich label semantics of ABSA.
Approach:	They propose to tackle various ABSA tasks in a unified generative framework . they propose to use annotation-style and extraction-style modeling to enable training .
Outcome:	The proposed framework achieves state-of-the-art on four ABSA tasks across multiple benchmark datasets.

Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment (2025.findings-emnlp)

Copied to clipboard

Jiahuan Pei, Fanghua Ye, Xin Sun, Wentao Deng, Koen Hindriks, Junxiao Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing work on large language models lacks scalability and assesses pedagogic quality.
Approach:	They propose a multi-agent workflow leveraging large language models to simulate interactive teaching-learning conversations.
Outcome:	The proposed workflow integrates teacher and learner agents, an interaction manager, and an evaluator to facilitate procedural learning and assess pedagogic quality.

Gold: A Global and Local-aware Denoising Framework for Commonsense Knowledge Graph Noise Detection (2023.findings-emnlp)

Copied to clipboard

Zheye Deng, Weiqi Wang, Zhaowei Wang, Xin Liu, Yangqiu Song

Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark (2022.findings-emnlp)

Challenge:	Existing methods to construct CSKGs with large semantic coverage are expensive and introduce spurious noise.
Approach:	They propose a denoising framework that incorporates entity semantic information, global rules, and local structural information from the CSKG.
Outcome:	The proposed framework outperforms baseline methods in noise detection tasks on synthetic noisy CSKG benchmarks.

Copied to clipboard

Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng

Dialogue Systems & Conversational Agents

Challenge:	a number of safety concerns hinder the deployment of open-domain dialog systems, such as offensive languages and toxic behaviors, such social bias is difficult to detect.
Approach:	They propose a Dial-Bias Framework for analyzing social bias in conversations . they introduce a Chinese social bias dialog dataset and conduct in-depth ablation studies .
Outcome:	The proposed framework is the first annotated Chinese social bias dialog dataset . the proposed framework also provides a fine-grained dialog bias measurement benchmark .

PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks (2023.acl-long)

Copied to clipboard

Weiwen Xu, Xin Li, Yang Deng, Wai Lam, Lidong Bing

Responsible & Trustworthy NLP

Challenge:	Experimental results on ten datasets across seven domains demonstrate the effectiveness of PeerDA.
Approach:	They propose a new approach which uses span pairs with the PR relation as the augmentation data for training.
Outcome:	The proposed approach achieves state-of-the-art results on ten datasets across seven domains.

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 .

RADAR: Risk-Aware Distilled Adaptive Routing for Efficient Short-Form Video Platform Ecosystem Governance (2026.acl-industry)

Copied to clipboard

Baoyu Jing, Zixuan Wang, Junwen Chen, Xin Dong, Bingfeng Deng

Green & Sustainable NLP

Challenge:	Existing solutions to address inefficiency in large-scale integrity enforcement on short-form video platforms require multiple specialized vertical modules .
Approach:	They propose a lightweight risk-aware routing framework that selectively releases low-risk content while dispatching high-risk instances to appropriate vertical modules.
Outcome:	The proposed framework selectively releases low-risk content while dispatching high-risk instances to appropriate vertical modules.

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song