Papers by Xing Zhou

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models? (2025.findings-acl)

Challenge:	Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands.
Approach:	They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability.
Outcome:	The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities.

Copied to clipboard

Xixian Yong, Jianxun Lian, Xiaoyuan Yi, Xiao Zhou, Xing Xie

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)

Challenge:	Existing benchmarks for large language models lack information asymmetry with real-world situations.
Approach:	They propose a benchmark to evaluate the human-like motivational and behavioral reasoning ability of LLMs with detailed, realistic situations.
Outcome:	The proposed benchmark compared LLMs with real-world scenarios on seven model families and found that the most advanced models struggle with understanding "love & belonging" needs.

Copied to clipboard

Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu

Unified Contextual Query Rewriting (2023.acl-industry)

Challenge:	closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges .
Approach:	They propose a framework that leverages collective intelligence from all large language models to evaluate each other.
Outcome:	a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost.

Copied to clipboard

Yingxue Zhou, Jie Hao, Mukund Rungta, Yang Liu, Eunah Cho, Xing Fan, Yanbin Lu, Vishal Vasudevan, Kellen Gillespie, Zeynab Raeesy

Paraphrasing

Challenge:	Large-scale conversational AI agents such as Alexa, Siri, and Google Assistant are becoming increasingly popular in real-world applications to assist users in daily life.
Approach:	They propose a unified contextual query rewriting model that unifies QR for friction reduction and contextual carryover . they leverage the text-to-text unified framework which uses independent tasks with weighted loss to account for task importance .
Outcome:	The proposed model reduces friction and contextual carryover by using multiple auxiliary tasks.

A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure (2020.acl-main)

Copied to clipboard

Longyin Zhang, Yuqing Xing, Fang Kong, Peifeng Li, Guodong Zhou

Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Challenge:	Text-level discourse parsing of discourse rhetorical structure (DRS) is a fundamental research topic in natural language processing.
Approach:	They propose a top-down neural architecture for text-level discourse parsing . they cast the parser as a recursive split point ranking task .
Outcome:	The proposed top-down approach is more suitable for text-level discourse parsing.

Copied to clipboard

Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang

Efficient Large Scale Language Modeling with Mixtures of Experts (2022.emnlp-main)

Challenge:	Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers.
Approach:	They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification.
Outcome:	The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification.

Copied to clipboard

Mikel Artetxe, Shruti Bhosale, Naman Goyal, Todor Mihaylov, Myle Ott, Sam Shleifer, Xi Victoria Lin, Jingfei Du, Srinivasan Iyer, Ramakanth Pasunuru, Giridharan Anantharaman, Xian Li, Shuohui Chen, Halil Akin, Mandeep Baines, Louis Martin, Xing Zhou, Punit Singh Koura, Brian O’Horo, Jeffrey Wang, Luke Zettlemoyer, Mona Diab, Zornitsa Kozareva, Veselin Stoyanov

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Challenge:	Mixture of Experts layers (MoEs) enable efficient scaling of language models . large autoregressive language models such as GPT-3 can be adapted to a wide range of tasks .
Approach:	They propose to use Mixture of Experts layers to enable efficient scaling of language models . they find that MoEs are substantially more compute efficient than dense models compared to MoE models - but only when they are more modestly trained .
Outcome:	The proposed model outperforms dense models in a wide range of tasks and domains.

Copied to clipboard

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach:	They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome:	The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.

Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation (2022.coling-1)

Copied to clipboard

Xiaolin Xing, Yu Hong, Minhan Xu, Jianmin Yao, Guodong Zhou

Multilinguality

Challenge:	Existing approaches to train NMT models rely on sparse parallel data . a variety of PC variants yield significant improvements for low-resource NMT .
Approach:	They propose to transfer well-trained NMT models to low-resource languages by bidirectionally-adaptive learning strategy . they divide inner constituents of Parent encoder into two "teams" aiming to adapt to characteristics of low- and high-resourced languages .
Outcome:	The proposed method improves on low-resource NMT models with a variety of PC variants.

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning (2025.emnlp-main)

Copied to clipboard

Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri

How to Set the Learning Rate for Large-Scale Pre-training? (2026.findings-acl)

Challenge:	Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks is suboptimal.
Approach:	They propose a generator-validator paradigm to iteratively generate-then-validate training data from language models to fine-tune stronger Table-Specialist models that can specialize in a given task, without using manually-labeled data.
Outcome:	The proposed model outperforms vanilla language models on diverse table tasks and can match or surpass GPT-4 level quality.

Copied to clipboard

Yunhua Zhou, Shuhao Xing, Junhao Huang, Xipeng Qiu, Qipeng Guo

A Joint Learning Framework for Restaurant Survival Prediction and Explanation (2022.emnlp-main)

Challenge:	Optimal configuration of the learning rate (LR) is a fundamental yet formidable challenge in large-scale pre-training.
Approach:	They propose a Fitting Paradigm and a Transfer Paradigme to investigate fit and transfer . they propose scalability and elucidate the reasons why module-wise parameter tuning underperforms .
Outcome:	The proposed model reduces the search complexity by reducing the search cost by lowering the search factor.

Copied to clipboard

Xin Li, Xiaojie Zhang, Peng JiaHao, Rui Mao, Mingyang Zhou, Xing Xie, Hao Liao

Explainability & Interpretability in NLP

Challenge:	Recent advances in deep learning have various models that research reviews and interactions for different kinds of tasks, such as predicting restaurant survival.
Approach:	They propose a joint learning framework for explainable restaurant survival prediction based on multi-modal data of user-restaurant interactions and users’ textual reviews.
Outcome:	The proposed framework improves on two datasets showing that it can model restaurant interactions and users’ textual reviews.

General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference (2020.findings-emnlp)

Copied to clipboard

Jingfei Du, Myle Ott, Haoran Li, Xing Zhou, Veselin Stoyanov

CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction (2026.findings-acl)

Challenge:	Large pre-trained language models are currently used for many NLP tasks . however, inference for these models requires significant computational resources .
Approach:	They propose to use a shared text encoder to amortize the computational cost of inference over multiple tasks.
Outcome:	The proposed method reduces the size of the extracted representations by a factor of 16 to store them for later use.

Copied to clipboard

Jun Gao, Yun Peng, Qian Qiao, Changhai Zhou, Yuhua Zhou, Shiyang Zhang, Shichao Weng, Zhenchang Xing, Xiaoxue Ren

Responsible & Trustworthy NLP

Challenge:	Existing code reasoning benchmarks evaluate final output correctness under a single implementation.
Approach:	They propose a Code Reasoning benchmark that evaluates code reasoning through implementation invariance and process transparency.
Outcome:	The proposed benchmarks lack implementation invariance and process transparency . they observe superficial execution where models arrive at correct outputs without reasoning .

Pretraining Context Compressor for Large Language Models with Embedding-Based Memory (2025.acl-long)

Copied to clipboard

Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao

ToViLaG: Your Visual-Language Generative Model is Also An Evildoer (2023.emnlp-main)

Challenge:	Efficient processing of long contexts in large language models is essential for real-world applications such as retrieval-augmented generation and in-context learning.
Approach:	They propose a decoupled compressor-LLM framework that preserves contextual information within condensed embedding representations.
Outcome:	The proposed framework outperforms baseline models in three domains and across eight datasets while adapting to different downstream LLMs.

Copied to clipboard

Xinpeng Wang, Xiaoyuan Yi, Han Jiang, Shanlin Zhou, Zhihua Wei, Xing Xie

Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Challenge:	Recent large-scale Visual-Language Generative Models (VLGMs) generate toxic content, e.g., offensive text and pornography images, raising significant ethical risks.
Approach:	They propose a bottleneck-based detoxification method to reduce toxicity while maintaining comparable generation quality.
Outcome:	The proposed method could reduce toxicity while maintaining comparable generation quality.

Copied to clipboard

Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li

AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking (2025.findings-emnlp)

Challenge:	Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach:	They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome:	The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.

Copied to clipboard

Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, Wei Lin

Information Retrieval

Challenge:	Existing automated generation methods exhibit Weak Applicability and Weak Scalability . existing methods are limited by their reliance on metadata from specific corpora .
Approach:	They propose an approach to generate scalable RAG benchmarks using corpus-agnostic methods . they propose a difficulty-guided metric that directs query evolution process .
Outcome:	The proposed approach evolves queries significantly more challenging than existing methods . it is able to dynamically increase difficulty, limiting scalability of the query .

RecMind: Large Language Model Powered Agent For Recommendation (2024.findings-naacl)

Copied to clipboard

Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Yanbin Lu, Xiaojiang Huang, Yingzhen Yang

A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization (2025.findings-acl)

Challenge:	Existing recommendations systems are limited in generalizing to new tasks due to model scale and data size constraints.
Approach:	They propose an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge to provide zero-shot personalized recommendations.
Outcome:	The proposed model outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.

Copied to clipboard

Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li

NeuralClassifier: An Open-source Neural Hierarchical Multi-label Text Classification Toolkit (P19-3)

Challenge:	Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache.
Approach:	They propose a retrieval-based method to reduce the memory footprint of LLMs . they propose Windowed Rotary Position Embedding and query-aware vector quantization .
Outcome:	The proposed method can achieve lower performance degradation with lower overhead compared to existing methods . it can reduce the memory footprint and access overhead of long context large language models .

Copied to clipboard

Liqun Liu, Funan Mu, Pengyu Li, Xin Mu, Jing Tang, Xingsheng Ai, Ran Fu, Lifeng Wang, Xing Zhou

Information Extraction & Text Mining

Challenge:	NeuralClassifier is a toolkit for hierarchical multi-label text classification.
Approach:	They propose a toolkit for neural hierarchical multi-label text classification . they use a variety of text encoders to implement the model .
Outcome:	The proposed model achieves comparable performance with reported results in the literature.

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Copied to clipboard

Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao

Retrieval Heads are Dynamic (2026.acl-long)

Challenge:	Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach:	They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome:	The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.

Copied to clipboard

Yuping Lin, Zitao Li, Yue Xing, Pengfei He, Yingqian Cui, Yaliang Li, Bolin Ding, Jingren Zhou, Jiliang Tang

Information Retrieval

Challenge:	Recent studies have identified "retrieval heads" in Large Language Models responsible for extracting information from input contexts.
Approach:	They propose to examine retrieval heads from a dynamic perspective . they establish that retrieval head activation is highly dynamic and functionally irreplaceable .
Outcome:	The proposed model's hidden state encodes a predictive signal for future retrieval head patterns, indicating an internal planning mechanism.

On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Copied to clipboard

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach:	They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome:	The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (2022.findings-emnlp)

Copied to clipboard

Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong

Discourse Parsing Enhanced by Discourse Dependence Perception (2022.aacl-main)

Challenge:	Existing methods for temporal sentence grounding ignore two crucial issues . 1) Boundary-bias: the video downsampling process may lose these two frames . 2) Reasoning-biases: such incorrect new boundary frames lead to the reasoning bias .
Approach:	They propose a siamese sampling mechanism to generate additional contextual frames . they use a reasoning strategy to learn the inter-relationship among these frames a .
Outcome:	Extensive experiments demonstrate the effectiveness of a new siamese sampling network on three challenging datasets.

Copied to clipboard

Yuqing Xing, Longyin Zhang, Fang Kong, Guodong Zhou

PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models (2026.findings-acl)

Challenge:	Top-down neural models still suffer from the top-down error propagation issue . previous studies gradually switch from feature-based machine learning methods to deep neural models .
Approach:	They propose a top-down framework that learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders.
Outcome:	The proposed framework learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders on a Chinese discourse corpus.

Copied to clipboard

Wenlong Shi, Jianxun Lian, Mingqi Wu, Haiming Qin, Mingyang Zhou, Xing Xie, Naipeng Chao, Hao Liao

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Challenge:	Existing research focuses on character-level settings and static evaluation formats fail to capture the complexity of everyday social interactions.
Approach:	They propose a dynamic simulation framework for evaluating and improving persona-level role-playing in large language models (LLMs).
Outcome:	The proposed framework leverages user-generated social content to construct a nuanced persona bank and elicits multi-turn, context-rich interactions within simulated social environments.

Copied to clipboard

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

Reasoning

Challenge:	Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach:	They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome:	Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data (2026.acl-long)

Copied to clipboard

Han Weng, Zhou Liu, Yuanfeng Song, Xiaoming Yin, Xing Chen, Wentao Zhang

Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG (2026.acl-long)

Challenge:	Existing benchmarks do not assess agents’ capabilities across data types . Existing tools only evaluate agents' ability to extract reasonable insights across data formats.
Approach:	They propose a multi-source benchmark to evaluate the performance of data analytics agents in handling diverse data sources.
Outcome:	The proposed agent performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights.

Copied to clipboard

Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, Xiao Huang

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models (2024.findings-naacl)

Challenge:	Retrieval-augmented generation (RAG) has been used for enhancing large language models with external knowledge.
Approach:	They propose a framework for mining efficient graph structures via hashing to enhance RAG . they adopt an inductive paradigm where global graph structure emerges from local hash collisions .
Outcome:	The proposed framework outperforms existing baselines while requiring no GPU resources or token budget.

Copied to clipboard

Zhenpeng Su, Zijia Lin, Baixue Baixue, Hui Chen, Songlin Hu, Wei Zhou, Guiguang Ding, Xing W

Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models (2024.acl-long)

Challenge:	Existing generative language models neglect an inherent challenge in text corpus during training, i.e., the imbalance between frequent tokens and infrequent ones.
Approach:	They propose a function to mitigate the imbalance between frequent and infrequent tokens . authors propose 'MiLe Loss' function to assess learning difficulty of tokens during training .
Outcome:	Experiments show that models with proposed model can improve on downstream benchmarks.

Copied to clipboard

Zhiwei He, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, Rui Wang

Multilinguality

Challenge:	Existing text watermarking technologies lack consistency when texts are translated into different languages.
Approach:	They propose a cross-lingual watermark removal attack to bypass watermarking by first obtaining a response from an LLM in a pivot language and then translating it into the target language.
Outcome:	The proposed method can remove watermarks without performance loss by obtaining a response from an LLM in a pivot language and then translating it into the target language.

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems (2024.naacl-long)

Copied to clipboard

Zhenpeng Su, Xing W, Wei Zhou, Guangyuan Ma, Songlin Hu

Aligning Large Language Models for Controllable Recommendations (2024.acl-long)

Challenge:	Existing studies on dialogue response selection focus on post-training and fine-tuning for cross-encoders.
Approach:	They propose a post-training technique tailored for dense encoders in dialogue response selection . they propose 'Dialogue Contextual Masking Auto-Encoder' which compresses dialogue semantics into dense vectors .
Outcome:	The proposed technique achieves state-of-the-art on two commonly evaluated benchmarks.

Copied to clipboard

Wensheng Lu, Jianxun Lian, Wei Zhang, Guanghua Li, Mingyang Zhou, Hao Liao, Xing Xie

MIND: A Large-scale Dataset for News Recommendation (2020.acl-main)

Challenge:	Existing literature focuses on integrating domain-specific knowledge into LLMs to enhance accuracy using a fixed task template.
Approach:	They propose a collection of supervised learning tasks augmented with labels derived from a conventional recommender model to improve LLMs’ proficiency in adhering to recommendation-specific instructions.
Outcome:	The proposed approach significantly improves the capability of LLMs to respond to instructions within recommender systems, reducing formatting errors while maintaining a high level of accuracy.

Copied to clipboard

Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou

Query-Aware Knowledge Retrieval via Hyperbolic Structuring (2026.acl-long)

Challenge:	Personalized news recommendation is an important technique for personalized news service.
Approach:	They propose to build a large-scale news recommendation dataset from Microsoft News . they demonstrate that news recommendation relies on the quality of news content understanding .
Outcome:	The proposed dataset contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body.

Copied to clipboard

Chuang Zhou, Junnan Dong, Yilin Xiao, Shengyuan Chen, Su Dong, di Yin, Xing Sun, Zhaozhuo Xu, Xiao Huang