Papers by Xing Hu

Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (2022.findings-emnlp)

Challenge:	Existing news recommendation methods use pre-trained language models to produce news vectors and user vectors.
Approach:	They propose an unsupervised pre-training paradigm with two tasks for user behavior modeling.
Outcome:	The proposed model improves on the real-world news benchmark.

Copied to clipboard

Han Guo, Bowen Tan, Zhengzhong Liu, Eric Xing, Zhiting Hu

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

Challenge:	Maximum likelihood estimation (MLE) is the predominant method for training text generation models.
Approach:	They propose a new RL formulation for text generation from the soft Q-learning perspective using path consistency learning to combine the best of on-/off-policy updates and learn effectively from sparse reward.
Outcome:	The proposed approach outperforms MLE and previous RL methods in a wide range of tasks.

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

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

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

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Query-as-context Pre-training for Dense Passage Retrieval (2023.emnlp-main)

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

Copied to clipboard

Xing W, Guangyuan Ma, Wanhui Qian, Zijia Lin, Songlin Hu

Information Retrieval

Challenge:	Existing methods to improve passage retrieval performance by using context-supervised pre-training are weakly correlated.
Approach:	They propose to use query-as-context pre-training to train passage-query pairs . they evaluate the pre-trained models on large-scale passage retrieval benchmarks .
Outcome:	The proposed technique improves performance on large-scale passage retrieval benchmarks and out-of-domain zero-shot benchmarks.

Uncertainty-Aware Semantic Augmentation for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Luxi Xing, Weihua Luo

To Judge or Not to Judge: Can Large Language Models Leverage the Dispute Focus in Legal Judgment? (2026.acl-long)

Challenge:	Existing methods for neural machine translation only observe one source sentence at training time . this discrepancy in data distribution leads to a formidable learning challenge .
Approach:	They propose an uncertainty-aware semantic augmentation approach to capture universal semantic information among multiple source sentences and enhance hidden representations with this information.
Outcome:	The proposed approach outperforms baseline and existing methods on translation tasks.

Copied to clipboard

Luoming Hu, Liang Yang, Jingjie Zeng, Zijie Xing

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts (2025.naacl-long)

Challenge:	Existing research on large language models for legal judgment prediction fails to address the complexity of civil judicial cases.
Approach:	They propose a framework that leverages the dispute focus to guide LLMs through a structured, judge-like cognitive workflow.
Outcome:	The proposed framework can guide LLMs through a structured, judge-like cognitive workflow.

Copied to clipboard

Zhenpeng Su, Xing W, Zijia Lin, Yizhe Xiong, Minxuan Lv, Guangyuan Ma, Hui Chen, Songlin Hu, Guiguang Ding

Psychology-guided Controllable Story Generation (2022.coling-1)

Challenge:	Large language models (LLMs) have been attracting much attention due to their impressive performance in all kinds of downstream tasks.
Approach:	They propose a mix-of-experts model that allows the model size to grow without raising training costs.
Outcome:	The proposed model outperforms existing models in perplexity and robustness tests.

Copied to clipboard

Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng

ChatEdit: Towards Multi-turn Interactive Facial Image Editing via Dialogue (2023.emnlp-main)

Challenge:	Existing controllable story generation systems ignore the psychological changes of the protagonists and focus on the appointed keywords or emotions.
Approach:	They propose a Psychology-guided Controllable Story Generation System (PICS) that generates stories that adhere to the given leading context and desired psychological state chains for the protagonist.
Outcome:	The proposed system outperforms baselines and shows that it can generate stories with more consistent psychological changes.

Copied to clipboard

Xing Cui, Zekun Li, Pei Li, Yibo Hu, Hailin Shi, Chunshui Cao, Zhaofeng He

Visual Data in NLP

Challenge:	Existing approaches to interactive facial image editing treat multi-turn editing as a sequence of successive single-turn edits, leading to attribute forgetting and error accumulation.
Approach:	They propose a framework for interactive facial image editing through dialogues based on the CelebA-HQ dataset and a benchmark dataset to evaluate this.
Outcome:	The proposed framework outperforms existing methods and improves existing ones.

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)

Copied to clipboard

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

Target-Guided Open-Domain Conversation (P19-1)

Challenge:	Existing approaches to program repair are based on correctness alone.
Approach:	They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome:	The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.

Copied to clipboard

Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric Xing, Zhiting Hu

Dialogue Systems & Conversational Agents

Challenge:	a new study aims to improve opendomain chat systems by integrating goals and strategy into the system.
Approach:	They propose a structured approach that introduces coarse-grained keywords to control intended content of system responses and attains smooth conversation transition through turn-level supervised learning.
Outcome:	The proposed system produces meaningful and effective conversations significantly better than other approaches.

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen

Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention (2022.emnlp-main)

Challenge:	Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach:	They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome:	The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .

Copied to clipboard

Wenhao Li, Xiaoyuan Yi, Jinyi Hu, Maosong Sun, Xing Xie

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Challenge:	Recent studies have shown that powerful Transformer architectures produce dull high-frequency phrases, severely hurting the diversity and novelty of generated text.
Approach:	They propose a method to control the sharpness of the attention distribution by python code and use it to learn a Bayesian approximation of posterior attention.
Outcome:	The proposed method improves diversity and novelty while maintaining comparable quality on conditional and unconditional generation tasks.

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Somanshu Singla, Zhen Wang, Tianyang Liu, Abdullah Ashfaq, Zhiting Hu, Eric Xing

Bi-directional CognitiveThinking Network for Machine Reading Comprehension (2020.coling-main)

Challenge:	Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts.
Approach:	They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses .
Outcome:	The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges.

Copied to clipboard

Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models (2023.emnlp-main)

Challenge:	Existing methods for reading comprehension are still in their infancy at the level of cognitive intelligence.
Approach:	They propose a bi-directional cognitive knowledge framework to simulate reverse thinking and inertial thinking in the brain to answer questions.
Outcome:	The proposed framework shows that bi-directional knowledge helps the QA task.

Copied to clipboard

Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Lee

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown unprecedented performance across various tasks.
Approach:	They propose an easy-to-use framework that integrates adapters into LLMs . they evaluate adapters on 14 datasets from two different reasoning tasks .
Outcome:	The proposed framework can be used to fine-tune open-access language models with task-specific data and instruction data.

Copied to clipboard

Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Kejiang Chen, Xing Hu

COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities (2022.coling-1)

Challenge:	Reasoning ability is a defining capability of Large Language Models (LLMs), but RLVR training suffers from policy entropy collapse, hindering exploration and limiting reasoning performance.
Approach:	They propose a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
Outcome:	The proposed framework outperforms baselines on multiple mathematical reasoning benchmarks.

Copied to clipboard

Yuqiang Xie, Yue Hu, Wei Peng, Guanqun Bi, Luxi Xing

Challenge:	Existing methods for modeling motivations, emotions and actions in language-based human activities have been limited.
Approach:	They propose to model motivations, emotions and actions in language-based human activities using a dataset called Story Commonsense.
Outcome:	The proposed model can better reveal the essential relationship between motivations, emotions and actions than existing methods.

Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks (2022.acl-short)

Copied to clipboard

Xing Wu, Chaochen Gao, Meng Lin, Liangjun Zang, Songlin Hu

Information Extraction & Text Mining

Challenge:	Experimental results show text smoothing outperforms data augmentation methods by a substantial margin.
Approach:	They propose to use a masked language model to convert a token to a smoothed representation by converting a sentence from its one-hot representation to 'controllable smoothes' they propose to combine text smoothing with other data augmentation methods to achieve better performance.
Outcome:	The proposed method outperforms mainstream data augmentation methods by a substantial margin on different datasets in a low-resource regime.

MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)

Copied to clipboard

Qing Wang, Xue Han, Jiahui Wang, Lehao Xing, Qian Hu, Lianlian Zhang, Chao Deng, Junlan Feng

DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization (2025.findings-naacl)

Challenge:	MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code.
Approach:	They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels.
Outcome:	The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources.

Copied to clipboard

Pucheng Dang, Xing Hu, Dong Li, Rui Zhang, Qi Guo, Kaidi Xu

ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)

Challenge:	Existing text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images.
Approach:	They propose a method which uses zeroth order optimization to procure gradient approximations and harnesses both C-PRV and D-PRv to enhance attack prompts within a discrete prompt space.
Outcome:	The proposed method achieves an 8.5% higher average attack success rate than previous works on multiple state-of-the-art safety mechanisms.

Copied to clipboard

Hao Chen, Haoze Li, Zhiqing Xiao, Lirong Gao, Qi Zhang, Xiaomeng Hu, Ningtao Wang, Xing Fu, Junbo Zhao

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

Challenge:	Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability.
Approach:	They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs.
Outcome:	The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads.

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 .

Learning to Compress Prompt in Natural Language Formats (2024.naacl-long)

Copied to clipboard

Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang, Zirui Liu, Xun Chen, Xia Hu

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization (2026.acl-long)

Challenge:	Existing work rely on compressing long contexts into soft prompts, but soft prompt compression encounters limitations in transferability . natural language (NL) prompts are incompatible with back-propagation, and NL prompts lack flexibility in imposing length constraints.
Approach:	They propose a framework that compresses long prompts into NL formatted Capsule Prompts.
Outcome:	The proposed framework reduces 81.4% of the original length, decreases inference latency up to 4.5x, and saves 80.1% of budget overheads while providing transferability across diverse LLMs and different datasets.

Copied to clipboard

Tiancheng Xing, Jerry Li, Yixuan Du, Xiyang Hu

ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Large language models (LLMs) are increasingly used as rerankers, but their ranking behavior can be steered by small, natural-sounding prompts.
Approach:	They propose a token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings.
Outcome:	The proposed method outperforms state-of-the-art base-lines and is hard to detect.

Copied to clipboard

Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, Songlin Hu

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022.emnlp-main)

Challenge:	a new method for learning unsupervised sentence embeddings is proposed . unsup-SimCSE is biased because of the length information encoded into the sentence embeds .
Approach:	They propose a new unsupervised sentence embedding method that uses dropout to obtain positive pairs from a pre-trained Transformer encoder.
Outcome:	The proposed method outperforms the state-of-the-art unsup-SimCSE on a STS task.

Copied to clipboard

Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric Xing, Zhiting Hu

Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affective Computing (P19-1)

Challenge:	Existing methods for finding the optimal prompt for a task are difficult to optimize.
Approach:	They propose an efficient discrete prompt optimization approach with reinforcement learning that generates the optimal discrete stimulus after training with reward.
Outcome:	The proposed approach is based on a parameter-efficient policy network that generates the optimal discrete prompt after training with reward.

Copied to clipboard

Sijie Mai, Haifeng Hu, Songlong Xing

Sentiment Analysis

Challenge:	Existing approaches to multimodal fusion are based on fusing features at holistic level instead of focusing on local and global interactions.
Approach:	They propose a general strategy called ‘divide, conquer and combine’ for multimodal fusion that combines local and global interactions in a hierarchy.
Outcome:	The proposed strategy achieves state-of-the-art performance on multimodal affective computing with higher efficiency.

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents (2026.findings-acl)

Copied to clipboard

Xing Fu, Yulin Hu, Mengtong Ji, Haozhen Li, Yixin Sun, Weixiang Zhao, Yanyan Zhao, Bing Qin

Information Retrieval

Challenge:	Existing research treats memory as a mechanism for factual retention, neglecting its role in shaping users’ emotional experiences.
Approach:	They propose a benchmark for evaluating Emotional Need-aware Proactive Memory Retrieval (ENPMR) it enables agents to infer users’ latent emotional needs and proactively retrieve appropriate memories to support empathetic interaction.
Outcome:	The proposed benchmark includes over 1,800 memory-augmented dialogues and defines structured mappings between emotional needs and supportive memory types.

Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation (2022.findings-emnlp)

Copied to clipboard

Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie

Can We Steer Reasoning Direction by Thinking Intervention? (2025.findings-emnlp)

Challenge:	Variational Auto-Encoder (VAE) has been widely adopted in text generation due to its ability to learn flexible representations.
Approach:	They propose a Transformer-based recurrent VAE structure that imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the posterior distribution with residual parameterization.
Outcome:	The proposed structure can deduce a non-zero lower bound of the KL term and enhance the entanglement of each segment and preceding latent variables, providing a theoretical guarantee of generation diversity.

Copied to clipboard

Xingsheng Zhang, Luxi Xing, Chen Zhang, Yanbing Liu, Yifan Deng, Yunpeng Li, Yue Hu, Chenxu Niu

RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval (2022.findings-emnlp)

Challenge:	Large Reason Models suffer from overthinking and erroneous reasoning problems due to the lack of fine-grained control over their reasoning behaviors.
Approach:	They propose a paradigm to enable fine-grained control over LRMs’ reasoning behaviors by aligning reasoning trajectories with specific cognitive patterns.
Outcome:	The proposed paradigm achieves integration intervention throughout model reasoning processes.

Copied to clipboard

Xing Wu, Chaochen Gao, Zijia Lin, Zhongyuan Wang, Jizhong Han, Songlin Hu

Fast Retrieval and Slow Reasoning for Explainable Multimodal Sentiment Analysis (2026.findings-acl)

Challenge:	sparse sampling of videos suffers from inter-modal redundancy and visual redundancies . et al., 2021) proposes to sparsestly sample frames from videos to alleviate temporal redundance .
Approach:	They propose to use sparse sampling to alleviate temporal redundancy in videos . they propose to penalize high-redundant video patches and text tokens .
Outcome:	The proposed method improves on four benchmark datasets.

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)

Challenge:	Existing multimodal sentiment analysis methods rely on holistic fusion . such strategies introduce redundant information and obscure the decision process .
Approach:	They propose an interpretable framework that decomposes multimodal sentiment modeling into two cooperative pathways.
Outcome:	The proposed framework achieves competitive performance, higher efficiency, stronger robustness to noise, and clearer decision transparency than existing holistic fusion methods.

Copied to clipboard

Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie

Multilinguality

Challenge:	Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates.
Approach:	They propose a ranking-oriented induction model to learn personalized mapping function for each word.
Outcome:	The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages.

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models (2025.acl-long)

Copied to clipboard

Jingxuan Zhang, Zhenhua Xu, Rui Hu, Wenpeng Xing, Xuhong Zhang, Meng Han

BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have raised critical concerns about model ownership and intellectual property protection.
Approach:	They propose a method for effectively removing backdoor-based fingerprints from LLMs . they propose deleting backdoor fingerprints using a transferable erasure mechanism .
Outcome:	The proposed method removes backdoor-based fingerprints while maintaining model performance.

Copied to clipboard

Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric Xing, Zhiting Hu

Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Challenge:	Existing methods to construct knowledge graphs are limited to a small set of relations due to manual cost or restrictions in text corpus.
Approach:	They propose to automatically construct knowledge graphs (KGs) of diverse new relations from pretrained language models that accept knowledge queries with prompts.
Outcome:	The proposed framework extracts knowledge of over 400 new relations from pretrained language models, including RoBERTaNet, with minimal input of a relation definition and a few shot of example entity pairs.

Copied to clipboard

Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu

A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)

Challenge:	Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach:	They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome:	The proposed approach achieves stronger performance than a range of comparison methods.

Copied to clipboard

Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Xiaodan Liang, Teruko Mitamura, Eric Xing, Zhiting Hu

Challenge:	Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP.
Approach:	They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation .
Outcome:	The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave .

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

Copied to clipboard

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

RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs (2024.naacl-demo)

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

Bowen Tan, Yun Zhu, Lijuan Liu, Hongyi Wang, Yonghao Zhuang, Jindong Chen, Eric Xing, Zhiting Hu

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

Challenge:	Recent advances in machine learning (ML) are attributed to large language models (LLMs), but their escalating memory requirements require developers to partition a large model to distribute it across multiple GPUs or TPUs.
Approach:	They propose a lightweight and user-friendly tool to automate distributed training and inference for LLMs and to simplify ML pipeline development.
Outcome:	The proposed tool automates distributed training and inference for LLMs, and simplifies ML pipeline development.

Copied to clipboard

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

Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation (2022.naacl-main)

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

Jinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie

Progressive Generation of Long Text with Pretrained Language Models (2021.naacl-main)

Challenge:	Variational Auto-Encoders are often used for text generation tasks due to the sequential nature of the text.
Approach:	They propose a variational Transformer framework that learns a series of layer-wise latent variables with each inferred from those of lower layers and tightly coupled with the hidden states by low-rank tensor product.
Outcome:	The proposed framework can learn latent variables from lower layers and incorporate more information.

Copied to clipboard

Bowen Tan, Zichao Yang, Maruan Al-Shedivat, Eric Xing, Zhiting Hu

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization (2025.emnlp-main)

Challenge:	Existing methods for "long" text generation are limited to outputs of 50-200 tokens . however, our proposed ProGen generates coherent long passages of text in a progressive manner .
Approach:	They propose a method for generating coherent long passages of text in a progressive manner . they first produce domain-specific content keywords and then refine them into complete passages . human evaluation validates that their proposed generation is more coherent .
Outcome:	The proposed method produces domain-specific content keywords and refines them into complete passages in multiple stages.

Copied to clipboard

Shuo Xing, Peiran Li, Yuping Wang, Ruizheng Bai, Yueqi Wang, Chan-Wei Hu, Chengxuan Qian, Huaxiu Yao, Zhengzhong Tu

Bridging the Temporal Gap in Multimodal LLMs: Deeply Stacking Temporal Tokens for Audio-Visual Speech Recognition (2026.findings-acl)

Challenge:	emergence of large Vision Language Models (VLMs) has broadened the capabilities of single-modal Large Language Model (LLM) but VLMs are prone to significant hallucinations, especially in the form of cross-modal inconsistencies.
Approach:	They propose a new alignment framework that leverages image retrieval to integrate both textual and visual preference signals.
Outcome:	The proposed framework mitigates hallucinations more effectively than previous methods . it maintains robustness and scalability across a wide range of VLM sizes and architectures .

Copied to clipboard

Liyong Wang, Junliang Xing, Tianyu Hu, Jianfei Jiang, Jihuai Zhao, Huimin Ma

Smoothed Contrastive Learning for Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Existing audio-visual speech recognition systems suffer from a temporal gap . visual speech patterns captured from lip movements provide complementary information that remains inherently robust to acoustic noise.
Approach:	They propose a framework that deeply stacks temporal tokens across both encoding and decoding stages to bridge this temporal gap.
Outcome:	The proposed framework outperforms existing supervised, self-supervised, and LLM-based methods by 6.1% on LRS2 and 7.8% on LLS3.

Copied to clipboard

Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu

Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation (2021.emnlp-main)

Challenge:	Unsupervised contrastive sentence embedding models use InfoNCE loss function . increasing batch size leads to performance degradation when it exceeds threshold .
Approach:	They propose a simple smoothing strategy upon the InfoNCE loss function to reduce the number of false-negative pairs in a batch without increasing the batch size.
Outcome:	The proposed smoothing strategy improves unsupervised SimCSE on semantic similarity tasks.

Copied to clipboard

Mingkai Deng, Bowen Tan, Zhengzhong Liu, Eric Xing, Zhiting Hu

ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models (2022.findings-emnlp)

Challenge:	Natural language generation (NLG) tasks have complex nature and require manual evaluation.
Approach:	They propose a unifying perspective based on the nature of information change in NLG tasks . they propose 'information alignment' metrics that can be used to evaluate different aspects of NLG .
Outcome:	The proposed metrics achieve stronger or comparable correlations with human judgement compared to state-of-the-art metrics in diverse tasks.

Copied to clipboard

Jiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric Xing, Zhiting Hu

Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach (2020.emnlp-main)

Challenge:	Existing approaches to data-to-text generation require limited training examples . a data-based approach is based on a set of pre-trained language models with optional finetuning.
Approach:	They propose a data-to-text generation task that makes use of any given (or no) examples.
Outcome:	The proposed approach improves on baselines on a dataset with zero/few/full-shot settings.

Copied to clipboard

Bowen Tan, Lianhui Qin, Eric Xing, Zhiting Hu

Low-Resource NLP

Challenge:	Existing studies on aspect-based abstractive summarization assume a small set of aspects and do not consider other diverse aspects.
Approach:	They propose a weak supervision construction method and an aspect modeling scheme to solve this problem.
Outcome:	The proposed method significantly expands the application of the task in practice.

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)

Copied to clipboard

Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang

Multilinguality

Challenge:	Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages.
Approach:	They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency.
Outcome:	Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting .

Graph Neural News Recommendation with Unsupervised Preference Disentanglement (2020.acl-main)

Copied to clipboard

Linmei Hu, Siyong Xu, Chen Li, Cheng Yang, Chuan Shi, Nan Duan, Xing Xie, Ming Zhou

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)

Challenge:	Existing methods to learn informative user and news representations fail to consider high-order connectivity underlying the user-news interactions.
Approach:	They propose a novel Graph Neural News Recommendation model with Unsupervised Preference Disentanglement which can encode high-order relationships into user and news representations by information propagation along the graph.
Outcome:	The proposed model can encode high-order relationships into user and news representations by information propagation along the graph and disentangle latent preference factors by a neighborhood routing algorithm.

Copied to clipboard

Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo

Challenge:	Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench .
Approach:	They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool .
Outcome:	The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions .

CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Zhuofan Chen, Jiyuan He, Yichi Zhang, Xing Hu, Haoxing Wen, Jun Bai, Wenge Rong

Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for generating high-quality, multi-step reasoning are limited . we present a new framework for synthesising rigorous, cognitively diverse problems .
Approach:	They propose a cognitive atom-based framework for synthesizing mathematically rigorous problems.
Outcome:	The proposed framework outperforms existing methods in accuracy, reasoning depth and diversity while exceeding the difficulty of AIME.

Copied to clipboard

Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou

InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings (2022.findings-emnlp)

Challenge:	Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging .
Approach:	They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning.
Outcome:	The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets.

Copied to clipboard

Xing Wu, Chaochen Gao, Zijia Lin, Jizhong Han, Zhongyuan Wang, Songlin Hu