Papers by Wei Pan

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning.
Approach:	They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures .
Outcome:	The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

LEMMA: Learning from Errors for MatheMatical Advancement in LLMs (2025.findings-acl)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu

Reasoning

Challenge:	Existing approaches focus on improving the quality of correct training data, neglecting the value contained in error data, thereby hindering the model’s reflective ability.
Approach:	They propose to improve LLM's reasoning ability by learning from error data and a grounded mistake augmentation method to collect representative errors.
Outcome:	The proposed model achieves significant performance improvements over other strong models with less than 90k data.

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)

Copied to clipboard

Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen

AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens.
Approach:	They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method.
Outcome:	The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs.

Copied to clipboard

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

Reasoning

Challenge:	Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach:	They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome:	The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Twitter Homophily: Network Based Prediction of User’s Occupation (P19-1)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Jiaqi Pan, Rishabh Bhardwaj, Wei Lu, Hai Leong Chieu, Xinghao Pan, Ni Yi Puay

Challenge:	Existing approaches to predicting Twitter users' demographic attributes exploit, select, and combine various features generated from text and network to achieve the best performance.
Approach:	They extend existing Twitter occupational class prediction data set and exploit social network homophily to achieve competitive performance.
Outcome:	The proposed method achieves better performance on a dataset with a small fraction of the training data.

Thinking Before You Speak: A Proactive Test-time Scaling Approach (2025.findings-emnlp)

Copied to clipboard

Cong Liu, Wenchang Chai, Hejun Wu, Yan Pan, Pengxu Wei, Liang Lin

Reasoning

Challenge:	Large Language Models often exhibit deficiencies with complex reasoning tasks, such as maths, due to the discrepancy between human reasoning patterns and those presented in training data.
Approach:	They propose to insert insights between consecutive reasoning steps to bridge this gap by generating insights between the next reasoning steps.
Outcome:	Experiments on mathematical datasets confirm the effectiveness of the proposed reasoning framework on complex problems.

AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval (2020.findings-emnlp)

Copied to clipboard

Chieh-Yang Chen, Pei-Hsin Wang, Shih-Chieh Chang, Da-Cheng Juan, Wei Wei, Jia-Yu Pan

Natural Language Interfaces

Challenge:	Existing neural task-oriented dialogue systems cannot be encoded by memory networks, such as memory networks.
Approach:	They propose an end-to-end trainable text-to SQL guided framework to learn a neural agent that interacts with KBs using the generated SQL queries.
Outcome:	The proposed method significantly improves on the AirDialogue dataset, which contains the conversations of customers booking flight tickets from the agent.

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities (2025.acl-long)

Copied to clipboard

Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, Fei Liu

Challenge:	Existing studies have focused on developing LLMs to automate complex planning tasks.
Approach:	They propose to provide a comprehensive overview of current LLM planners to fill this gap . they examine performance criteria including completeness, executability, optimality, representation, generalization, and efficiency .
Outcome:	The proposed survey examines performance criteria for LLM planners and highlights their strengths and weaknesses.

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)

Copied to clipboard

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

LLM-Based Multi-Agent Systems are Scalable Graph Generative Models (2025.findings-acl)

Challenge:	None. None.. None!
Approach:	None. None.. None!
Outcome:	None. None. No. :

Copied to clipboard

Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, Bolin Ding

LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models (2024.naacl-demo)

Challenge:	Social graphs are mathematical structures stem from pairwise interactions between entities through nodes and edges.
Approach:	They propose a framework for dynamic, text-attributed social graph generation that simulates the temporal node and edge generation processes for zero-shot social graphs.
Outcome:	The proposed framework improves macroscopic graph structure metrics by 11% . the proposed model can generate graphs with up to 100,000 nodes or 10 million edges .

Copied to clipboard

Shizhe Diao, Rui Pan, Hanze Dong, KaShun Shum, Jipeng Zhang, Wei Xiong, Tong Zhang

Context-aware Entity Typing in Knowledge Graphs (2021.findings-emnlp)

Challenge:	Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches.
Approach:	They propose a toolkit to simplify the finetuning of general foundation models.
Outcome:	The proposed toolkit simplifies the domain- and task-aware finetuning of general foundation models with limited computing resources.

Copied to clipboard

Weiran Pan, Wei Wei, Xian-Ling Mao

Knowledge Representation

Challenge:	Existing methods for knowledge graph entity typing are embedding-based and graph convolutional networks (GCNs) . Existing approaches for knowledge Graph Entity Typing (KGET) are incomplete and require multiple inference mechanisms.
Approach:	They propose a method that uses entities’ contextual information to infer missing types in knowledge graphs by using two inference mechanisms: N2T and Agg2T.
Outcome:	The proposed method can infer entities' missing types by completing two real-world KGs.

Towards Universal Debiasing for Language Models-based Tabular Data Generation (2025.findings-emnlp)

Copied to clipboard

Tianchun Li, Tianci Liu, Xingchen Wang, Rongzhe Wei, Pan Li, Lu Su, Jing Gao

Responsible & Trustworthy NLP

Challenge:	Existing large language models have exacerbated fairness issues in tabular data generation . inherent historical biases in tabulated data cause LLMs to exacerbate fairness problems .
Approach:	They propose a universal debiasing framework that minimizes group-level dependencies . it leverages the autoregressive structure and analytic sampling distributions of LLM-based tabular data generators .
Outcome:	The proposed framework minimizes group-level dependencies while reducing mutual information between advantaged and protected attributes.

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs (2026.acl-long)

Copied to clipboard

Xuanwen Ding, Chengjun Pan, Zejun Li, Jiwen Zhang, Siyuan Wang, Zhongyu Wei

Green & Sustainable NLP

Challenge:	Evaluating multimodal large language models (MLLMs) is becoming increasingly expensive as benchmarks grow in scale and cross-modality complexity.
Approach:	They propose an adaptive evaluation framework for efficient benchmarking that treats evaluation as an interview-like process by keeping a hypothesized ability structure of the evaluated model and actively selecting the informative questions.
Outcome:	Experiments on four representative multimodal benchmarks show that **A2-Judger significantly improves sample efficiency while maintaining reliable evaluation results.

Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification (2022.coling-1)

Copied to clipboard

Wei Huang, Chen Liu, Bo Xiao, Yihua Zhao, Zhaoming Pan, Zhimin Zhang, Xinyun Yang, Guiquan Liu

Text Classification

Challenge:	Existing methods for hierarchical text classification are lacking in the field of natural language processing.
Approach:	They propose a hierarchy-aware T5 model with path-adaptive attention mechanism to exploit hierarchical dependency across different levels.
Outcome:	The proposed model outperforms state-of-the-art models especially in Macro-F1 and low Macro.

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Wei Wu, Zhuoshi Pan, Kun Fu, Chao Wang, Liyi Chen, Yunchu Bai, Tianfu Wang, Zheng Wang, Hui Xiong

Responsible & Trustworthy NLP

Challenge:	Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios.
Approach:	They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation .
Outcome:	The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead.

Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

Multilinguality

Challenge:	Existing unsupervised neural machine translation systems can degrade when labeled data is limited.
Approach:	They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset.
Outcome:	The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU.

A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)

Copied to clipboard

Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng

Challenge:	Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance .
Approach:	They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy.
Outcome:	The proposed model will be able to detect human-written content in real time.

Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Copied to clipboard

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

Knowledge Distillation Transfer Sets and their Impact on Downstream NLU Tasks (2022.emnlp-industry)

Challenge:	Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models.
Approach:	This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy .
Outcome:	The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications.

Copied to clipboard

Charith Peris, Lizhen Tan, Thomas Gueudre, Turan Gojayev, Pan Wei, Gokmen Oz

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

Challenge:	Domain Classification (DC) and Intent Classification/Named Entity Recognition (ICNER) are the most common methods for reducing teacher-student knowledge into manageable sizes for low-latency downstream applications.
Approach:	They investigate whether distillation from a generic LM benefits downstream tasks . a domain classification and a task-specific data set are used to fine tune the model .
Outcome:	The proposed model improves across tasks and test sets when only task-specific data is used.

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li

Structured Data in NLP

Challenge:	Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach:	They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome:	The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.

Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis (2023.tacl-1)

Copied to clipboard

Yanyan Wang, Qun Chen, Murtadha H.M. Ahmed, Zhaoqiang Chen, Jing Su, Wei Pan, Zhanhuai Li

Sentiment Analysis

Challenge:	Recent work shows that Aspect-Term Sentiment Analysis (ATSA) can be performed by Gradual Machine Learning (GML) but the current unsupervised solution is limited by inaccurate knowledge conveyance.
Approach:	They propose a supervised approach which leverages binary polarity relations between instances to enable supervised knowledge conveyance.
Outcome:	The proposed approach outperforms pure DNN solutions on real benchmark data.

Multi-Granularity Fusion Text Semantic Matching Based on WoBERT (2024.lrec-main)

Copied to clipboard

Hongchun Yu, Wei Pan, Xing Fan, Hanqi Li