Papers by Jing Zheng

CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)

Challenge:	Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions.
Approach:	They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information .
Outcome:	The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities.

Copied to clipboard

Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Challenge:	Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach:	They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome:	The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions (2024.naacl-demo)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah Goodman, Christopher Manning, Christopher Potts

Explainability & Interpretability in NLP

Challenge:	Existing libraries are often project-based, but pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others.
Approach:	They propose an open-source Python library that supports customizable interventions on a range of different PyTorch modules.
Outcome:	The proposed framework provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others.

An Empirical Study of Memorization in NLP (2022.acl-long)

Copied to clipboard

Xiaosen Zheng, Jing Jiang

Linguistic Theories

Challenge:	Existing studies see memorization as hindering generalization in deep learning models.
Approach:	They propose a long-tail theory to explain the memorization behavior of deep learning models . they use three different NLP tasks to test whether the theory holds .
Outcome:	The proposed long-tail theory is validated in three NLP tasks and shows it is faithful.

R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)

Copied to clipboard

Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo

AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)

Challenge:	Existing models with stacked layers do not explicitly model hierarchical structure of language understanding.
Approach:	They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process.
Outcome:	The proposed model can predict words given their left and right abstraction nodes.

Copied to clipboard

Junjie Wang, Yicheng Chen, Wangshu Zhang, Sen Hu, Teng Xu, Jing Zheng

Green & Sustainable NLP

Challenge:	Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications.
Approach:	They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter.
Outcome:	Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation.

CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning (2025.findings-acl)

Copied to clipboard

Xikang Guan, Zheng Gu, Jing Huo, Tianyu Ding, Yang Gao

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

Challenge:	Existing methods for visual-to-music generation lack large-scale, high-quality visual-music paired datasets and lack of direct semantic correspondence between visuals and music.
Approach:	They propose a framework that distills Chain-of-Thought reasoning to enable visual-to-music generation without paired data.
Outcome:	The proposed framework achieves optimal performance on image-to-music and video-to music tasks.

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

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

Pengwei Zhan, Jing Yang, He Wang, Chao Zheng, Xiao Huang, Liming Wang

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

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Challenge:	Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction .
Approach:	They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction.
Outcome:	The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks.

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

Reasoning

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Copied to clipboard

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

Reasoning

Challenge:	Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach:	They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome:	The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.

From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026.findings-acl)

Copied to clipboard

Jing Zhang, Lianghong Guo, Yanlin Wang, Terry Yue Zhuo, Yong Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi, Yuchi Ma, Hongyu Zhang, Zibin Zheng

Natural Language Interfaces

Challenge:	Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries.
Approach:	They conduct preliminary analysis of real user–LLM dialogues from WildChat to investigate the importance of Dev Knowledge QA in AI-assisted software development scenarios.
Outcome:	The proposed benchmark is based on real user–LLM dialogues from WildChat.

MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents (2026.findings-eacl)

Copied to clipboard

Shuyi Zhang, Zhenbin Chen, Shuting Li, Kewei Tu, Li Jing, Zixia Jia, Zilong Zheng

Information Extraction & Text Mining

Challenge:	Existing document-level information extraction systems operate at the sentence level or within narrow domains due to annotation constraints.
Approach:	They propose a large-scale universal dataset for multi-domain, document-level information extraction from long texts.
Outcome:	The proposed dataset integrates traditional knowledge bases with large language models to extract fine-grained entities, aliases, and relation triples across 34 domains.

FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding (2022.acl-long)

Copied to clipboard

Yanan Zheng, Jing Zhou, Yujie Qian, Ming Ding, Chonghua Liao, Li Jian, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, Zhilin Yang

Subtopic-driven Multi-Document Summarization (D19-1)

Challenge:	Existing evaluation protocols for few-shot natural language understanding (NLU) tasks are inconsistent and hinder fair comparison and measuring progress.
Approach:	They propose an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability.
Outcome:	The proposed framework improves evaluation procedures in three key aspects, i.e., performance, dev-test correlation, and stability.

Copied to clipboard

Xin Zheng, Aixin Sun, Jing Li, Karthik Muthuswamy

Information Extraction & Text Mining

Challenge:	Experimental results show that the proposed model outperforms state-of-the-art methods on benchmark datasets.
Approach:	They propose a multi-document summarization model that assumes a set of documents to be summarized is on the same topic.
Outcome:	The proposed model outperforms state-of-the-art methods on benchmark datasets.

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning (2024.findings-naacl)

Copied to clipboard

Yinger Zhang, Hui Cai, Xierui Song, Yicheng Chen, Rui Sun, Jing Zheng

Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing (2023.findings-acl)

Challenge:	Existing approaches to enable large language models to implement function calling are limited in their tool-use capabilities.
Approach:	They propose a controllable, target-driven approach to empower LLMs to operate external APIs only via prompts.
Outcome:	The proposed approach limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion.

Copied to clipboard

Jing Zheng, Jyh-Herng Chow, Zhongnan Shen, Peng Xu

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Challenge:	Sequence-to-sequence (seq2sequ) models have been successful in semantic parsing tasks but struggle on out-of-distribution data.
Approach:	They propose to use a large-scale dialogue dataset to evaluate compositional generalization of semantic parsing.
Outcome:	The proposed model outperforms BART- and T5-based models on the SMCalflow-CS dataset on the zero-shot learning task.

Copied to clipboard

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song

Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network (2022.acl-long)

Challenge:	a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach:	They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome:	a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .

Copied to clipboard

Zheng Gong, Kun Zhou, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen

Improving Knowledge Production Efficiency With Question Answering on Conversation (2023.acl-industry)

Challenge:	a fundamental challenge in modeling math problems is how to fuse semantics of textual description and formulas.
Approach:	They propose a method to continually pre-train language models for improving understanding of math problems with syntax-aware memory networks.
Outcome:	The proposed approach outperforms competitive baselines on four math tasks.

Copied to clipboard

Changlin Yang, Siye Liu, Sen Hu, Wangshu Zhang, Teng Xu, Jing Zheng

Natural Language Interfaces

Challenge:	Existing researches on conversation-based QA focus on document-based tasks . current researche focuses on document based tasks, but there is a lack of researche on conversation based qa .
Approach:	They propose a multi-span extraction model on conversation-based QA and introduce continual pre-training and multi-task learning schemes to further improve model performance.
Outcome:	The proposed model outperforms baseline on two Chinese datasets and will be released for research purposes.

Towards Unifying Reference Expression Generation and Comprehension (2022.emnlp-main)

Copied to clipboard

Duo Zheng, Tao Kong, Ya Jing, Jiaan Wang, Xiaojie Wang

PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)

Challenge:	Existing models for REG and REC have distinct inputs and connections between them . a new model for REg and reprehension is needed to solve these problems .
Approach:	They propose a unified model for REG and REC that fuses image, region and text . they propose Vision-conditioned Masked Language Modeling and Text-Conditioned Region Prediction .
Outcome:	The proposed model outperforms existing models on REG and REC tasks.

Copied to clipboard

Pengwei Zhan, Chao Zheng, Jing Yang, Yuxiang Wang, Liming Wang, Yang Wu, Yunjian Zhang

Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval (2023.emnlp-main)

Challenge:	Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario.
Approach:	They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance.
Outcome:	The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time.

Copied to clipboard

Peitian Zhang, Zheng Liu, Shitao Xiao, Zhicheng Dou, Jing Yao

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)

Challenge:	Inverted file structure is a common technique for accelerating dense retrieval, but its lossy nature degrades it.
Approach:	They propose a hybrid index where embedding clusters and salient terms work collaboratively to accelerate dense retrieval.
Outcome:	The proposed method achieves lossless retrieval quality with competitive efficiency across index settings.

Copied to clipboard

Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song

Green & Sustainable NLP

Challenge:	Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability.
Approach:	They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones.
Outcome:	The proposed framework shows that it is robust to different prompts and superior to previous methods.

Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? (2025.acl-long)

Copied to clipboard

Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, Jiawei Han

An Alignment-Agnostic Model for Chinese Text Error Correction (2021.findings-emnlp)

Challenge:	Graph Neural Networks (GNNs) with CLIP pipeline are difficult because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and conceptual gaps between domains.
Approach:	They propose a multi-modal prompt learning paradigm to adapt pre-trained GNNs to downstream tasks with weak text supervision.
Outcome:	The proposed model can generalize graphs to unseen classes with weak text supervision.

Copied to clipboard

Liying Zheng, Yue Deng, Weishun Song, Liang Xu, Jing Xiao

Syntactic Text Processing

Challenge:	Existing models for Chinese text error correction can correct mistaken, missing and redundant characters, but they cannot handle missing or redundant characters.
Approach:	They propose an alignment-agnostic framework to correct Chinese text errors . framework detects missing and redundant characters and can be used as a cold start model .
Outcome:	The proposed framework can handle both text aligned and non-aligned situations and can serve as a cold start model when no annotation data are provided.

Self-Adjust Softmax (2025.emnlp-main)

Copied to clipboard

Chuanyang Zheng, Yihang Gao, Guoxuan Chen, Han Shi, Jing Xiong, Xiaozhe Ren, Chao Huang, Zhenguo Li, Yu Li

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)

Challenge:	Usually, tokens with larger attention scores are important for the final prediction.
Approach:	They propose to modify softmax(z) to z softmax and its normalized variant to improve the Transformer attention mechanism by making minor adjustments to the softmax function.
Outcome:	The proposed model provides enhanced gradient properties compared to the vanilla softmax function.

Copied to clipboard

Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu

Visual Data in NLP

Challenge:	Recent VSE models combine simple pooling methods with hard triplet loss to improve performance.
Approach:	They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods.
Outcome:	The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval.

Rethinking Word-level Adversarial Attack: The Trade-off between Efficiency, Effectiveness, and Imperceptibility (2024.lrec-main)

Copied to clipboard

Pengwei Zhan, Jing Yang, He Wang, Chao Zheng, Liming Wang

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)

Challenge:	Neural language models have demonstrated impressive performance but remain vulnerable to word-level adversarial attacks.
Approach:	They propose two standardized search spaces to address the problem of word-level adversarial attacks.
Outcome:	The proposed search spaces improve performance and trade-offs in different scenarios.

Copied to clipboard

Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness (2021.emnlp-main)

Challenge:	Extensive experiments demonstrate that treating attention as a feature map and applying convolution as . a processing method significantly enhances Transformer performance.
Approach:	They propose to use the convolution operator to mimic the processing methods in computer vision to treat attention as a feature map and apply it to neighboring attention scores across different heads.
Outcome:	The proposed model can be adapted to various attention-related models and achieves high performance.

Copied to clipboard

Hengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao, Lu Su, Bo Li

Robustness in NLP

Challenge:	a recent study shows that inappropriate language can cause models to output profanity . authors propose a training framework to prevent such outputs from hurting the usability of models .
Approach:	proposed training framework eliminates the causes that trigger the generation of profanity . authors propose a framework that leverages a short list of profans to prevent this .
Outcome:	a proposed training framework can prevent models from generating profanity . the proposed framework leverages a short list of profanities examples .

FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning (2022.acl-long)

Copied to clipboard

Jing Zhou, Yanan Zheng, Jie Tang, Li Jian, Zhilin Yang

R2H: Building Multimodal Navigation Helpers that Respond to Help Requests (2023.emnlp-main)

Challenge:	Existing methods for text data augmentation are limited to simple tasks and weak baselines.
Approach:	They propose a data augmentation method FlipDA that uses a generative model and a classifier to generate label-flipped data.
Outcome:	The proposed method improves many tasks while not negatively affecting the others.

Copied to clipboard

Yue Fan, Jing Gu, Kaizhi Zheng, Xin Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing dialog-based embodied datasets are not sufficient to develop intelligent navigation-helper agents capable of navigating users in unfamiliar areas.
Approach:	They introduce a novel benchmark, Respond to Help Requests, to promote the development of multi-modal navigation helpers capable of responding to requests for help . they also propose two approaches to construct the navigation-helper agent, including fine-tuning a task-oriented multi-mod response generation model that can see and respond, named SeeRee, and employing . a multi-module large language model in a zero-shot manner.
Outcome:	The proposed model outperforms the baseline model and the proposed model on two tasks based on human evaluations and automatic benchmarking.

A Universal Discriminator for Zero-Shot Generalization (2023.acl-long)

Copied to clipboard

Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng, Zhilin Yang