Papers by Jiwei Li

ConRPG: Paraphrase Generation using Contexts as Regularizer (2021.emnlp-main)

Challenge:	Many natural language processing tasks can be formulated as deep reinforcement learning (DRL) problems.
Approach:	This tutorial provides an introduction to the foundations of deep reinforcement learning . it describes recent advances in designing deep reinforcement for NLP .
Outcome:	This tutorial provides an introduction to the foundations of deep reinforcement learning and some practical solutions for NLP tasks.

Copied to clipboard

Yuxian Meng, Xiang Ao, Qing He, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, Jiwei Li

Text Generation

Challenge:	Existing methods for paraphrase generation lack reliable supervision signals.
Approach:	They propose an unsupervised paradigm for paraphrase generation based on contextual language models, candidate filtering and paraphrase model training based upon the selected candidates.
Outcome:	The proposed paradigm outperforms existing paraphrase generation methods in supervised and unsupervised setups.

Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning (2025.findings-acl)

Copied to clipboard

Shuhe Wang, Guoyin Wang, Yizhong Wang, Jiwei Li, Eduard Hovy, Chen Guo

Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models (2026.findings-acl)

Challenge:	Packing is an optimization technique that optimizes training time and resources by combining different training sequences to fit the model’s maximum input length.
Approach:	They perform extensive comparisons between packing and padding methods, covering datasets ranging from 69K to 1.2M and models from 8B to 70B.
Outcome:	The proposed method has been shown to improve training efficiency while maintaining performance.

Copied to clipboard

Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang, Heng Tao Shen

Exploring and Adapting Chinese GPT to Pinyin Input Method (2022.acl-long)

Challenge:	Existing automatic prompt optimization methods fail to optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements.
Approach:	They propose a dynamic prompt optimization framework for complex reasoning that unifies prompt templates and decodes hyperparameters as inheritable agent configurations.
Outcome:	Experiments on multiple mathematical and hybrid reasoning benchmarks show that Agent-GWO improves accuracy and stability over existing prompt optimization methods.

Copied to clipboard

Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi

An MRC Framework for Semantic Role Labeling (2022.coling-1)

Challenge:	a frozen GPT can generate state-of-the-art performance on perfect pinyin, but performance drops when input includes abbreviated pinyan, which links to even larger number of Chinese characters.
Approach:	They propose to use Chinese GPT to generate fluent sentences using abbreviated pinyin.
Outcome:	The proposed approach improves on abbreviated pinyin across all domains.

Copied to clipboard

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He

Semantic Parsing

Challenge:	Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach:	They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome:	The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .

Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction (2022.emnlp-main)

Copied to clipboard

Zhen Wan, Qianying Liu, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Jiwei Li

Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension (2021.findings-emnlp)

Challenge:	Existing RE models are incapable of handling implicit expressions and long-tail relation types due to language complexity and data sparsity.
Approach:	They propose a method to enhance relation extraction using k nearest neighbors (kNN-RE) kNN is a nearest-neighbor search tool that allows the model to consult training relations at test time .
Outcome:	The proposed model outperforms the best model to date on ACE05, SciERC, and Wiki80 datasets and outperformed the best on i2b2 and Wik80 dataset.

Copied to clipboard

Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao, Qing He

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings (2026.acl-long)

Challenge:	unified Aspect-based Sentiment Analysis (ABSA) aims to couple aspect terms with their corresponding opinion terms, which might make it easier to predict sentiment polarities.
Approach:	They propose a new paradigm to pair aspect terms with their corresponding opinion terms . they propose to use a machine learning paradigm to solve the unified ABSA task .
Outcome:	The proposed framework can solve the ABSA task without any additional data annotation or transformation.

Copied to clipboard

Minsik Oh, Jiwei Li, Guoyin Wang

kFolden: k-Fold Ensemble for Out-Of-Distribution Detection (2021.emnlp-main)

Challenge:	Annotating and gathering utterance relationships in dialogues is difficult, while token-level annotations, entities, slots and templates, are much easier to obtain.
Approach:	They propose a template-aware augmentation method that utilizes template information to learn utterance embeddings via self-supervised contrastive learning framework.
Outcome:	The proposed method improves on five benchmark dialogue datasets and shows that it is more efficient than previous SOTA methods.

Copied to clipboard

Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang

Text Classification

Challenge:	Existing studies studying OOD detection in NLP often rely on external data to diversify model predictions.
Approach:	They propose a framework which mimics OOD detection behavior without external data . they take text classification as an archetype and compare them to existing datasets .
Outcome:	The proposed framework can resolve in- and out-distribution examples in a natural way using existing datasets.

Fast Nearest Neighbor Machine Translation (2022.findings-acl)

Copied to clipboard

Yuxian Meng, Xiaoya Li, Xiayu Zheng, Fei Wu, Xiaofei Sun, Tianwei Zhang, Jiwei Li

Machine Translation

Challenge:	Fast kNN-MT uses the entire corpus as the datastore for the nearest neighbor search . knn-MT is two-orders slower than vanilla MT models .
Approach:	They propose a fast kNN-MT model that uses the entire corpus as the datastore for nearest neighbor search.
Outcome:	The proposed model is two-orders faster than kNN-MT and is only two times slower than the standard model.

Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints (D18-1)

Copied to clipboard

Ashutosh Baheti, Alan Ritter, Jiwei Li, Bill Dolan

Dialogue Systems & Conversational Agents

Challenge:	Neural conversation models tend to generate safe, generic responses for most inputs . this is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation.
Approach:	They propose a distributional constraint approach that incorporates side information into the generated responses.
Outcome:	The proposed approach generates responses that are less generic without sacrificing plausibility.

Ranking-Enhanced Unsupervised Sentence Representation Learning (2023.acl-long)

Copied to clipboard

Yeon Seonwoo, Guoyin Wang, Changmin Seo, Sajal Choudhary, Jiwei Li, Xiang Li, Puyang Xu, Sunghyun Park, Alice Oh

GPT-RE: In-context Learning for Relation Extraction using Large Language Models (2023.emnlp-main)

Challenge:	Unsupervised sentence representation learning has progressed through contrastive learning and data augmentation methods such as dropout masking.
Approach:	They propose a novel unsupervised sentence encoder, RankEncoder, which predicts the semantic vector of an input sentence by leveraging its relationship with other sentences in an external corpus.
Outcome:	The proposed unsupervised sentence encoder achieves 80.07% Spearman’s correlation, a 1.1% improvement over the previous state-of-the-art system.

Copied to clipboard

Zhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu, Haiyue Song, Jiwei Li, Sadao Kurohashi

ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information (2021.acl-long)

Challenge:	Existing approaches to in-context learning (ICL) are lacking in relation extraction (RE) . emergence of large language models (LLMs) such as GPT-3 represents a significant advancement in natural language processing.
Approach:	They propose to incorporate task-aware representations into demonstration retrieval and enrich the demonstrations with gold label-induced reasoning logic.
Outcome:	The proposed model achieves SOTA and competitive performances on the Semeval and SciERC datasets.

Copied to clipboard

Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li

Paraphrase Generation as Unsupervised Machine Translation (2022.coling-1)

Challenge:	ChineseBERT model incorporates glyph and pinyin information of Chinese characters into pretraining . proposed model achieves new performance boost over baseline models with fewer training steps .
Approach:	They propose a ChineseBERT model that incorporates glyph and pinyin information into pretraining . the glyph embedding is obtained based on different fonts of a character, and the pinyink embeddment characterizes the pronunciation of Chinese characters.
Outcome:	The proposed model achieves new performance boosts over baseline models with fewer training steps.

Copied to clipboard

Xiaofei Sun, Yufei Tian, Yuxian Meng, Nanyun Peng, Fei Wu, Jiwei Li, Chun Fan

Text Generation

Challenge:	Existing methods for paraphrase generation rely on labeled datasets or are limited in narrow domains.
Approach:	They propose a paradigm for paraphrase generation by treating the task as unsupervised machine translation based on pairs of unlabeled monolingual sentences.
Outcome:	The proposed paradigm can generate paraphrases on a large unlabeled monolingual corpus without relying on bilingual sentence pairs.

BertGCN: Transductive Text Classification by Combining GNN and BERT (2021.findings-acl)

Copied to clipboard

Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, Fei Wu

Information Retrieval

Challenge:	Text classification is a core task in natural language processing (NLP) Graph neural networks (GNNs) serve as an effective approach for transductive learning.
Approach:	They propose a model that combines large scale pretraining and transductive learning for text classification.
Outcome:	The proposed model achieves SOTA performance on a wide range of datasets.

Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis (2021.findings-acl)

Copied to clipboard

Guoxin Yu, Xiang Ao, Ling Luo, Min Yang, Xiaofei Sun, Jiwei Li, Qing He

DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)

Challenge:	Existing studies aim to integrate multiple sub-tasks into a unified ABSA model but suffer from major disadvantages .
Approach:	They propose a multi-task learning approach to make use of sub-tasks for a unified ABSA.
Outcome:	The proposed model can work well when some sub-tasks are absent, and the interactive relations among subtasks not adequate.

Copied to clipboard

Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng

Challenge:	Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk.
Approach:	They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression.
Outcome:	The proposed method surpasses state-of-the-art methods on long context tasks.

Triggerless Backdoor Attack for NLP Tasks with Clean Labels (2022.naacl-main)

Copied to clipboard

Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Yi Yang, Shangwei Guo, Chun Fan

Robustness in NLP

Challenge:	Backdoor attacks are a new threat to neural natural language processing models due to the fragility and lack of interpretability of NLP models.
Approach:	They propose a method to perform backdoor attacks without an external trigger . they propose to use clean-labeled examples to generate poisoned clean-labelled examples .
Outcome:	The proposed strategy is effective and hard to defend due to its triggerless nature.

CorefQA: Coreference Resolution as Query-based Span Prediction (2020.acl-main)

Copied to clipboard

Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

GPT-NER: Named Entity Recognition via Large Language Models (2025.findings-naacl)

Challenge:	Existing coreference resolution models suffer from mention proposal.
Approach:	They propose a query-based span prediction task that can retrieve mentions left out at the mention proposal stage.
Outcome:	The proposed model can retrieve mentions left out at the mention proposal stage and improve generalization capability using existing question answering datasets.

Copied to clipboard

Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, Guoyin Wang, Chen Guo

Layer-wise Model Pruning based on Mutual Information (2021.emnlp-main)

Challenge:	Large-scale language models (LLMs) have shown impressive ability for in-context learning with limited training data.
Approach:	They propose a novel sequence labeling task that transforms a sequence labeled as a text-generation task into a self-verification task that LLMs can adapt to.
Outcome:	The proposed model performs better on NER than supervised models on a variety of tasks . the proposed model can be easily adapted by LLMs to generate a text sequence .

Copied to clipboard

Chun Fan, Jiwei Li, Tianwei Zhang, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun

Entity-Relation Extraction as Multi-Turn Question Answering (P19-1)

Challenge:	In spite of impressive results of neural networks, the huge model size has hindered their applications in cases where computation and memory resources are limited.
Approach:	They propose a method for layer-wise pruning using mutual information based feature selection in SVMs and logistic regression.
Outcome:	The proposed pruning strategy offers greater speedup and higher performance than weight-based pruning methods.

Copied to clipboard

Xiaoya Li, Fan Yin, Zijun Sun, Xiayu Li, Arianna Yuan, Duo Chai, Mingxin Zhou, Jiwei Li

Natural Language Interfaces

Challenge:	Identifying entities and their relations is the prerequisite of extracting structured knowledge from unstructured raw texts.
Approach:	They propose a new paradigm for the task of entity-relation extraction . they cast the task as a multi-turn question answering problem .
Outcome:	The proposed paradigm significantly outperforms previous best models on the ACE and CoNLL04 datasets.

Copied to clipboard

Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

Low-Resource NLP

Challenge:	Existing methods to measure sentence similarity face limited dataset size and training-test gap . existing methods lack large-scale labeled datasets with labeles that are labor-intensive and expensive .
Approach:	They propose a framework that measures sentence similarity by comparing probabilities of generating two sentences given the same context.
Outcome:	The proposed framework achieves significant performance boosts over baselines under supervised and unsupervised settings.

Deep Adversarial Learning for NLP (N19-5)

Copied to clipboard

William Yang Wang, Sameer Singh, Jiwei Li

Robustness in NLP

Challenge:	Adversarial learning is a game-theoretic learning paradigm that has achieved huge successes in the field of Computer Vision recently.
Approach:	This tutorial introduces the foundations of deep adversarial learning and some practical problems and solutions in NLP.
Outcome:	This tutorial introduces the foundations of deep adversarial learning and some practical problems and solutions in NLP.

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

Text Classification via Large Language Models (2023.findings-emnlp)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, Guoyin Wang

Low-Resource NLP

Challenge:	Large-scale Language Models (LLMs) have shown the ability for in-context learning.
Approach:	They propose a progressive reasoning strategy tailored to addressing complex linguistic phenomena such as intensification, contrast, irony and limited number of tokens allowed in in-context learning.
Outcome:	The proposed model performs better on 4 out of 5 widely-used text-classification benchmarks, while demonstrating comparable performance to SOTA on MR.

OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)

Copied to clipboard

Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu

Dice Loss for Data-imbalanced NLP Tasks (2020.acl-main)

Challenge:	Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model .
Approach:	They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias.
Outcome:	The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones.

Copied to clipboard

Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, Jiwei Li

Syntactic Text Processing

Challenge:	Using dice loss, we find that data imbalance is a common issue in many NLP tasks . data imbalance affects the performance of many tasks, such as tagging and machine reading comprehension .
Approach:	They propose to use dice loss to replace the standard cross-entropy objective for data-imbalanced NLP tasks.
Outcome:	The proposed training objective achieves significant performance boost on a wide range of data imbalanced tasks.

A Unified MRC Framework for Named Entity Recognition (2020.acl-main)

Copied to clipboard

Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, Jiwei Li

Situated Embedding Models for Context-Aware Dense Retrieval (2026.acl-short)

Challenge:	Named entity recognition is divided into nested NER and flat NER depending on whether entities are nesting.
Approach:	They propose to formulate named entity recognition task as machine reading comprehension task instead of sequence labeling problem .
Outcome:	The proposed framework achieves vast amount of performance boost over current models on nested and flat NER datasets.

Copied to clipboard

Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu

Representation Learning

Challenge:	Existing embedding models are not well-equipped to encode situated context effectively, i.e., situating a chunk’s meaning within its context.
Approach:	They propose to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.
Outcome:	The proposed model outperforms state-of-the-art embedding models on a book-plot retrieval dataset.

Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries (2022.coling-1)

Copied to clipboard

Xiaofei Sun, Zijun Sun, Yuxian Meng, Jiwei Li, Chun Fan

Text Generation

Challenge:	Existing models focus on local word prediction, and cannot make high level plans on what to generate.
Approach:	They propose a pipelined system that summarises, outlines and elaborates on each bullet point to generate the corresponding segment.
Outcome:	The proposed system produces long texts with significantly better quality and faster convergence speed.

RAISE: Reinforced Adaptive Instruction Selection For Large Language Models (2025.findings-emnlp)

Copied to clipboard

Qingsong Lv, Yangning Li, Zihua Lan, Zishan Xu, Jiwei Tang, Tingwei Lu, Yinghui Li, Wenhao Jiang, Hong-Gee Kim, Hai-Tao Zheng, Philip S. Yu