Papers by Siyu Wang

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Challenge:	Existing Large Language Models (LLMs) mainly address isolated tasks such as emotion analysis or stance detection.
Approach:	They propose a large-scale model that combines large-level annotations with hyperbolic space to model human cognitive states.
Outcome:	The proposed model outperforms baseline models on cognitive dimensions on single dimension tasks while retaining strong hierarchical structure.

Copied to clipboard

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

Automatic Keyphrase Generation by Incorporating Dual Copy Mechanisms in Sequence-to-Sequence Learning (2022.coling-1)

Copied to clipboard

Siyu Wang, Jianhui Jiang, Yao Huang, Yin Wang

Aspect-to-Scope Oriented Multi-view Contrastive Learning for Aspect-based Sentiment Analysis (2023.findings-emnlp)

Challenge:	Existing models for keyphrase generation use a copy mechanism to generate keyphrases, but they do not identify key words in the source text and copy them to create more keyphrase.
Approach:	They propose a dual-copier keyphrase generation model that uses a sequence-to-sequence model to generate keyphrases for a piece of text.
Outcome:	The proposed model outperforms baseline models and achieves an obvious performance improvement.

Copied to clipboard

Heyan Chai, Ziyi Yao, Siyu Tang, Ye Wang, Liqiang Nie, Binxing Fang, Qing Liao

TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models (2026.acl-long)

Challenge:	Existing methods for Aspect-based sentiment analysis (ABSA) focus on mining syntactic or semantic information, which suffers from noisy interference when multiple aspects exist in a sentence.
Approach:	They propose a scope-assisted multi-view graph contrastive learning framework that captures correlation and difference between aspect and syntactic/semantic information.
Outcome:	The proposed framework outperforms state-of-the-art methods on five benchmark datasets and verifies its effectiveness and robustness.

Copied to clipboard

Yulong Wang, Siyu Zhao

Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)

Challenge:	Existing PEFT methods can be costly and underfit token-level contexts.
Approach:	They propose a PEFT method that performs fine-grained, token-specific edits with a small additional inference overhead and minimal tuning.
Outcome:	The proposed method outperforms state-of-the-art methods in 8 tasks and GLUE with a minimal tuning overhead and inference overhead.

Copied to clipboard

Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang

Representation Learning

Challenge:	Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach:	They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome:	The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.

Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification (2026.acl-long)

Copied to clipboard

Bowei Zhang, Hanbing Liu, Qixin Tian, Siyu Chen, Ziyuan Wang, Qi Qi

Responsible & Trustworthy NLP

Challenge:	Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries.
Approach:	They propose a framework that integrates LLM-based generation with Lean-based auto-formalization and verification.
Outcome:	LeVer is the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and verification.

RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference (2026.acl-long)

Copied to clipboard

Siran Liu, Guoxia Wang, Sa Wang, Jinle Zeng, Haoyang Xie, Siyu Lou, Jiabin Yang, Dianhai Yu, Haifeng Wang, Chao Yang

Visual Data in NLP

Challenge:	Existing approaches to dynamic sparse attention require preprocessing, lack global evaluation, violate query independence, or incur high computational overhead.
Approach:	They propose a dynamic sparse attention method that achieves all desirable properties through a head round-robin (RR) sampling strategy.
Outcome:	Experiments on natural language understanding and multimodal video comprehension show that the proposed method achieves 2.4 speedup at 128K context length outperforming existing methods.

Integrating Group-based Preferences from Coarse to Fine for Cold-start Users Recommendation (2025.coling-main)

Copied to clipboard

Siyu Wang, Jianhui Jiang, Jiangtao Qiu, Shengran Dai

Challenge:	Existing approaches to cross-domain recommendation (CDR) draw on historical purchase records or reviews to generate user representations.
Approach:	They propose a model that integrates preferences from coarse to fine levels to improve recommendations for cold-start users.
Outcome:	The proposed model outperforms state-of-the-art approaches on three CDR tasks.

Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach (2024.lrec-main)

Copied to clipboard

Siyu Duan, Jun Wang, Qi Su

CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V (2025.findings-naacl)

Challenge:	despite efforts to preserve cultural relics, many ancient artefacts have fallen prey to ravages of time, natural deterioration, or deliberate human actions.
Approach:	They propose a multimodal multitask restoration model that uses visual and context understanding to restore ancient texts.
Outcome:	The proposed model predicts damaged characters and generates restored images simultaneously.

Copied to clipboard

Siyu Xu, Yunke Wang, Daochang Liu, Bo Du, Chang Xu

CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models (2025.emnlp-main)

Challenge:	Recent advances in generative AI have suggested that by taking visual prompts, GPT-4V can demonstrate significant proficiency in visual recognition tasks.
Approach:	They propose a collage prompting task that collages multiple images into a single visual prompt and makes GPT-4V perform visual recognition on several images simultaneously.
Outcome:	The proposed task reduces the cost associated with GPT-4V's visual recognition . the proposed task group images of the same category together leads to better visual recognition results .

Copied to clipboard

Runze Li, Siyu Wu, Jun Wang, Wei Zhang

Explainability & Interpretability in NLP

Challenge:	Knowledge Tracing (KT) aims to model a student’s learning state over time and predict their future performance.
Approach:	They propose a framework that harnesses Large Language Models to enhance both prediction accuracy and explainability by a synergistic optimization loop.
Outcome:	The proposed framework improves both prediction accuracy and explainability by using a synergistic optimization loop.

A Hierarchical Sequence-to-Set Model with Coverage Mechanism for Aspect Category Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Siyu Wang, Jianhui Jiang, Shengran Dai, Jiangtao Qiu

Sentiment Analysis

Challenge:	Aspect category sentiment analysis (ACSA) aims to detect aspect categories and their corresponding sentiment polarities (category-sentiment pairs) generative models face three challenges, including addressing the missing predictions and focusing on relevant sentiment words.
Approach:	They propose to use sequence-to-set learning to tackle all three challenges simultaneously.
Outcome:	The proposed model is able to detect aspect categories and their corresponding sentiment polarities (category-sentiment pairs) but it is unable to predict all aspect categories within a sentence due to the disordered set.

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Copied to clipboard

Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, Rahul Mazumder

Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach:	They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome:	The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.

Copied to clipboard

Junyi Chen, Shihao Bai, Zaijun Wang, Siyu Wu, Chuheng Du, Hailong Yang, Ruihao Gong, Shengzhong Liu, Fan Wu, Guihai Chen

Green & Sustainable NLP

Challenge:	Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach:	They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome:	The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .

Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation (2025.findings-emnlp)

Copied to clipboard

Weiyuan Li, Xintao Wang, Siyu Yuan, Rui Xu, Jiangjie Chen, Qingqing Dong, Yanghua Xiao, Deqing Yang

Challenge:	a recent study has focused on simple settings, but their reliability in complex tasks remains understudied.
Approach:	They propose to use large language models as judges to evaluate reliability in complex tasks . they use a challenge benchmark to expose and quantify Auxiliary Information Induced Biases .
Outcome:	The proposed benchmark exposes and quantifies Auxiliary Information Induced Biases across 12 basic and 3 advanced scenarios.

CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)

Challenge:	Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language.
Approach:	They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension.
Outcome:	The proposed model fails to extract and utilize contextual information to improve understanding of images.

Copied to clipboard

Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao

Challenge:	Existing methods focus on knowledge and linguistic patterns of characters.
Approach:	They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits.
Outcome:	The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits.

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Copied to clipboard

MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Information Extraction & Text Mining

Challenge:	Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach:	They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome:	The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents (2025.acl-long)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

Pinyi Zhang, Siyu An, Lingfeng Qiao, Yifei Yu, Jingyang Chen, Jie Wang, Di Yin, Xing Sun, Kai Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing research has focused on role-playing agents’ ability to portray specified characters, but their ability to advance the plot requires substantial improvements to deliver more engaging interaction.
Approach:	They propose a role-playing framework to evaluate and enhance the plot-progression capabilities of role-players.
Outcome:	The proposed framework improves RPAs’ ability to time plot developments and yields a significant increase in conversation turns and sustained higher arousal levels.

CMT-Eval: A Novel Chinese Multi-turn Dialogue Evaluation Dataset Addressing Real-world Conversational Challenges (2025.findings-emnlp)

Copied to clipboard

Siyu Tian, Kaijie Mo, Yupei Wang, Renfen Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing evaluation benchmarks fail to capture users’ evolving needs and how their diverse conversation styles affect the dialogue flow.
Approach:	They propose to use CMT-Eval to evaluate Chinese multi-turn dialogue systems.
Outcome:	The proposed dataset is the first dedicated dataset for fine-grained evaluation of Chinese multi-turn dialogue systems.

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification (2021.emnlp-main)

Copied to clipboard

Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, Shujian Huang, Jiajun Chen

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works (2024.emnlp-main)

Challenge:	Large-scale multi-label text classification tasks often face long-tailed label distributions, where many labels have few or even no training instances.
Approach:	They propose a meta-learning approach that incorporates the objective of adapting to new low-resource tasks into the meta-Learning phase.
Outcome:	The proposed approach achieves state-of-the-art against strong baselines and can still enhance powerful BERTlike models.

Copied to clipboard

Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, Deqing Yang

Towards Preference Following in Tool Calling Language Agents (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have catalyzed numerous AI applications, among which role-playing agents (RPAs) are particularly popular.
Approach:	They propose to evaluate LLMs' character understanding capability via the character profiling task, i.e., summarizing character profiles from corresponding materials, a widely adopted yet understudied practice for RPA development.
Outcome:	The proposed model outperforms existing models and literature summarization methods and proves its ability to understand fictional characters in downstream tasks.

Copied to clipboard

Zhi-Yuan Chen, Siyu Lu, Qianlong Xie, Xingxing Wang, Yankai Lin

Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation (2026.acl-industry)

Challenge:	Currently, large language model (LLM)-based agents can't follow user preferences when calling tools.
Approach:	They propose a benchmark to evaluate agents' ability to identify personalized user preferences from interaction histories and to adhere to these preferences when calling tools.
Outcome:	The proposed model achieves 51.16% accuracy on the APOLLO benchmark, while GPT-4o achieves only 51.13% accuracy.

Copied to clipboard

Ji Hun Wang, Siyu Wu

Machine Translation

Challenge:	In practice, LLMs are largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints.
Approach:	They propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs.
Outcome:	The proposed framework improves both COMET and CometKiwi scores over one-stage evaluation methods while severities and error spans show strong agreement with human annotations and human editor preferences.

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension (2020.coling-main)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Siyu Long, Ran Wang, Kun Tao, Jiali Zeng, Xinyu Dai

Reasoning

Challenge:	Experimental results show that our model achieves state-of-the-art performance for Chinese idiom comprehension.
Approach:	They propose a model that can mitigate the inconsistency between literal and literal meanings by incorporating the synonym knowledge enhanced reader into the model.
Outcome:	The proposed model achieves state-of-the-art on a Chinese idiom reading comprehension dataset.

Human-Agent Collaborative Paper-to-Page Crafting (2026.findings-acl)

Copied to clipboard

Qianli Ma, Siyu Wang, Chen Yilin, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang

Challenge:	Existing approaches to create project pages from academic papers have focused on static slides and posters, but the dynamic nature of webpages remains an unaddressed challenge.
Approach:	They propose a novel multi-agent system that deconstructs paper-to-page creation into a coarse-to fine pipeline from narrative planning to multimodal content generation and interactive rendering.
Outcome:	The proposed system generates high-quality, visually appealing pages in under 15 minutes for less than $0.1 .

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models (2024.findings-acl)

Copied to clipboard

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	Multi-Modal Knowledge Graphs (MMKGs) are knowledge graphs that integrate and align information from diverse modalities (e.g., text and images).
Approach:	They propose a framework that integrates image-text pairs of long-tailed entities and a concept guidance module that offers explainability and enables human verification.
Outcome:	The proposed framework improves the accuracy of recognizing long-tailed image-text pairs compared to baselines and also offers flexibility and explainability.

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

Character is Destiny: Can Persona-assigned Language Models Make Personal Choices? (2025.findings-emnlp)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Rui Xu, Xintao Wang, Jiangjie Chen, Siyu Yuan, Xinfeng Yuan, Jiaqing Liang, Zulong Chen, null Xiaoqingdong, Yanghua Xiao