Papers by Yubo Wang

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning (2025.emnlp-main)

Challenge:	Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT).
Approach:	They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM.
Outcome:	The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%.

Copied to clipboard

Yu Wang, Shiwan Zhao, Zhihu Wang, Ming Fan, Xicheng Zhang, Yubo Zhang, Zhengfan Wang, Heyuan Huang, Ting Liu

Information Retrieval

Challenge:	Existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning.
Approach:	They introduce a module extension that integrates application-aware reasoning into the RAG pipeline.
Outcome:	Experiments show that RAG+ outperforms standard RAG variants and achieves gains of 3–5% in complex scenarios.

MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)

Copied to clipboard

Chenhao Wang, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora.
Approach:	They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization .
Outcome:	The proposed method improves the generalization performance of large langugae models.

Unleashing the Reasoning Potential of LLMs by Critique Fine-Tuning on One Problem (2025.emnlp-main)

Copied to clipboard

Yubo Wang, Ping Nie, Kai Zou, Lijun Wu, Wenhu Chen

CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Challenge:	Critique Fine-Tuning (CFT) is a promising paradigm for unlocking the reasoning capabilities of large language models.
Approach:	They propose a method that leverages critique data generated from a single math problem to improve reasoning accuracy.
Outcome:	The proposed method surpasses one-shot RLVR while requiring 15 to 20 times less compute.

Copied to clipboard

Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao

CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language Models (2022.emnlp-main)

Challenge:	Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach:	They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome:	The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.

Copied to clipboard

Chenhao Wang, Jiachun Li, Yubo Chen, Kang Liu, Jun Zhao

Forest Before Trees: Latent Superposition for Efficient Visual Reasoning (2026.acl-long)

Challenge:	Existing commonsense knowledge graphs are limited to English, hindering research in non-English languages.
Approach:	They propose a Chinese CKG generated from multilingual PLMs that is translated into Chinese . they propose 'generate-by-category' strategy to reduce invalid generation .
Outcome:	The proposed CKG has high quality and diversity, surpassing the direct translation version of similar English CKGs.

Copied to clipboard

Yubo Wang, Juntian Zhang, Yichen Wu, Yankai Lin, Nils Lukas, Yuhan Liu

Visual Data in NLP

Challenge:	Recent latent reasoning methods suffer from a bandwidth bottleneck . explicit textual rationales suffer from premature semantic collapse .
Approach:	They propose a new paradigm that reformulates visual deduction via Dynamic Windowed Alignment Learning.
Outcome:	The proposed paradigm achieves state-of-the-art performance among latent reasoning methods surpassing the strong baseline Monet by 5.03% on average.

FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation (2026.acl-long)

Copied to clipboard

Yubo Shan, Kun Zhang, Qiming Xu, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li, Yuanzhuo Wang

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)

Challenge:	Existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image-text generation.
Approach:	They propose a benchmark dedicated to evaluating factual consistency in interleaved image-text generation.
Outcome:	The proposed framework outperforms existing evaluation methods in evaluating factual consistency in interleaved image-text generation.

Copied to clipboard

Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Challenge:	Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning.
Approach:	They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module'
Outcome:	The proposed method outperforms SOTA baselines on two commonsense reasoning tasks.

Copied to clipboard

Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, Kai Chen, Dahua Lin, Jiaqi Wang

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach:	They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome:	The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge (2025.acl-long)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, William Yang Wang

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)

Challenge:	Existing studies solve this challenge by updating benchmarks with newly collected data, but they fail to guarantee contamination-free evaluation as the newly collected knowledge may contain pre-existing knowledge.
Approach:	They propose an automated anti-leakage benchmarking framework that builds and updates benchmarks without human labor instead of using newly collected data.
Outcome:	The proposed framework significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs.

Copied to clipboard

Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue

Augmentation, Retrieval, Generation: Event Sequence Prediction with a Three-Stage Sequence-to-Sequence Approach (2022.coling-1)

Challenge:	Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales.
Approach:	They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning.
Outcome:	The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks.

Copied to clipboard

Bo Zhou, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, Jiexin Xu, Xiaojian Jiang, Qiuxia Li

Information Retrieval

Challenge:	Existing methods to predict event sequences are complex and ignore the knowledge of external events.
Approach:	They propose a statistical induction problem to generate a sequence of events by exploring the similarity between the given goal and known sequences of events.
Outcome:	The proposed model outperforms existing methods on an event sequence prediction task.

MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities (2022.acl-demo)

Copied to clipboard

Yubo Ma, Zehao Wang, Mukai Li, Yixin Cao, Meiqi Chen, Xinze Li, Wenqi Sun, Kunquan Deng, Kun Wang, Aixin Sun, Jing Shao

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (2025.acl-long)

Challenge:	Recent Knowledge Graphs (KGs) store billions of world facts in a directed graph, but expression ability of such entity-centric KGs is limited.
Approach:	They propose a large-scale multi-modal event knowledge graph named MMEKG that unifies different modalities of knowledge via events.
Outcome:	The proposed system unifies different modalities of knowledge via events, which complement and disambiguate each other.

Copied to clipboard

Xiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Botao Yu, Ge Zhang, Huan Sun, Yu Su, Wenhu Chen, Graham Neubig

Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives (2025.findings-acl)

Challenge:	Recent advances in multimodal large language models have led to progress in tackling complex reasoning tasks that combine textual and visual information.
Approach:	They introduce a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark.
Outcome:	The proposed model performs lower on MMMU-Pro than on the previous benchmark, ranging from 16.8% to 26.9%.

Copied to clipboard

Zhihu Wang, Shiwan Zhao, Yu Wang, Heyuan Huang, Sitao Xie, Yubo Zhang, Jiaxin Shi, Zhixing Wang, Hongyan Li, Junchi Yan

Challenge:	Existing approaches to solving complex tasks with large language models (LLMs) fail to decompose tasks accurately or execute subtasks effectively.
Approach:	They propose a Chain-of-Learning (CoL) paradigm that highlights task dependencies on specific capability items, further broken down into their constituent knowledge and skill components.
Outcome:	The proposed model improves Yi-1.5-9B and Llama3-Chinese-8B for legal tasks by 45.00% and 24.50% on different domains.

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation (2024.findings-emnlp)

Copied to clipboard

Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

Information Retrieval

Challenge:	Recent advances in Large Language Models have transformed ML/AI development . a reevaluation of AutoML principles for Retrieval-Augmented Generation (RAG) systems is needed.
Approach:	They propose a framework for hyper-parameter tuning and a hierarchical MAB method for efficient exploration of large search spaces.
Outcome:	The proposed framework outperforms baseline methods in more challenging optimization scenarios.

Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation (2025.emnlp-main)

Copied to clipboard

Yubo Xie, Chenkai Wang, Zongyang Ma, Fahui Miao

Reconstructing Event Regions for Event Extraction via Graph Attention Networks (2020.aacl-main)

Challenge:	Large language models (LLMs) are trained on vast amounts of text from the Internet, but do they understand the viral content that rapidly spreads online?
Approach:	They introduce a dataset for CHinese Internet Meme Explanation that includes popular phrase-based memes from the Chinese Internet.
Outcome:	The proposed dataset includes popular phrase-based memes from the Chinese Internet, annotated with detailed information on their meaning, origin, example sentences, types, etc.

Copied to clipboard

Pei Chen, Hang Yang, Kang Liu, Ruihong Huang, Yubo Chen, Taifeng Wang, Jun Zhao

Probing into the Root: A Dataset for Reason Extraction of Structural Events from Financial Documents (2021.eacl-main)

Challenge:	Existing approaches for event extraction focus on sentence-level event extraction, but they lack a broader view of the document context.
Approach:	They build graphs with candidate event filler extractions enriched by sentential embeddings as nodes and use graph attention networks to identify event regions in a document and aggregate event information.
Outcome:	The proposed method performs well on two languages and shows that it is faster than previous methods.

Copied to clipboard

Pei Chen, Kang Liu, Yubo Chen, Taifeng Wang, Jun Zhao

MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026.acl-long)

Challenge:	Existing methods for event reason extraction are far from resolving this problem.
Approach:	They propose a task to extract causal explanations from document-level texts . they use a dataset FinReason for evaluation to provide Reasons annotation for financial events .
Outcome:	The proposed task performs better than existing methods on a dataset of 8,794 documents, 12,861 financial events and 11,006 reason spans.

Copied to clipboard

Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu

Incremental Event Detection via Knowledge Consolidation Networks (2020.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks.
Approach:	They propose to use a multi-turn reasoning evaluation framework to cover multi-turn interactions with the environments of large language models.
Outcome:	The proposed framework covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments.

Copied to clipboard

Pengfei Cao, Yubo Chen, Jun Zhao, Taifeng Wang

Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation (2024.findings-emnlp)

Challenge:	Existing approaches to event detection require a fixed set of pre-defined event types . existing methods cannot handle semantic ambiguity and training data imbalance problems .
Approach:	They propose a Knowledge Consolidation Network to address these issues . they propose to use a prototype enhanced retrospection and hierarchical distillation to mitigate the adverse effects of semantic ambiguity and class imbalance.
Outcome:	The proposed method outperforms the state-of-the-art model by 19% and 13.4% of whole F1 score on ACE and TAC benchmarks.

Copied to clipboard

Zehao Wang, Minye Wu, Yixin Cao, Yubo Ma, Meiqi Chen, Tinne Tuytelaars

Document-level Event Extraction via Parallel Prediction Networks (2021.acl-long)

Challenge:	a new evaluation framework for vision-language navigation is proposed . current evaluation standards hinge on endpoint success rates and path alignment metrics .
Approach:	They propose a semi-automatic method for CFG construction with Large-Language Models . they induct data spanning five principal instruction categories and analyze them .
Outcome:	The proposed framework diagnoses current models for the Vision-Language Navigation task at a finer-grained level.

Copied to clipboard

Hang Yang, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Taifeng Wang

Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering (2024.findings-emnlp)

Challenge:	Document-level event extraction (DEE) is indispensable when events are described throughout a document.
Approach:	They propose a document-level event extraction model that can extract structured events from a text in parallel.
Outcome:	The proposed model outperforms current state-of-the-art methods on a document-level event extraction task.

Copied to clipboard

Yubo Wang, Xueguang Ma, Wenhu Chen

Do LLMs Know and Understand Domain Conceptual Knowledge? (2025.findings-emnlp)

Challenge:	Large-scale language models (LLMs) like ChatGPT have demonstrated impressive abilities in generating responses based on human instructions. however, their use in the medical domain can be challenging due to their lack of specific, in-depth knowledge.
Approach:	They propose a system that integrates authoritative medical textbooks into LLMs’ framework using plug-and-play modules.
Outcome:	The proposed system outperforms the specialized Med-PaLM 2 model on three medical QA tasks by 11.6% to 16.6%.

Copied to clipboard

Sijia Shen, Feiyan Jiang, Peiyan Wang, Yubo Feng, Yuchen Jiang, Chang Liu

CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet (2021.acl-demo)

Challenge:	Concept sememe tree is a hierarchical structure that represents lexical meaning by combining sememes and their relationships.
Approach:	They introduce a Neighbor Semantic Structure (NSS) and a Chain-of-Thought prompting method to evaluate the effectiveness of various Large Language Models (LLMs) in generating concept sememe trees.
Outcome:	The proposed method guides LLMs through an analysis of a term’s intrinsic core concepts, essential attributes, and semantic relationships, enabling the generation of concept sememe trees.

Copied to clipboard

Zhuoran Jin, Yubo Chen, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Jun Zhao

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction (2022.acl-long)

Challenge:	CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge.
Approach:	They propose an information extraction toolkit called CogIE that is a bridge connecting raw texts and CogNet.
Outcome:	The proposed toolkit can ground raw texts to CogNet and leverage different types of knowledge to enrich extracted results.

Copied to clipboard

Yubo Ma, Zehao Wang, Yixin Cao, Mukai Li, Meiqi Chen, Kun Wang, Jing Shao

SciAgent: Tool-augmented Language Models for Scientific Reasoning (2024.emnlp-main)

Challenge:	Using a prompt-based model, we find that event argument extraction is efficient and generalized well to few-shot settings.
Approach:	They propose a model PAIE for event argument extraction using prompt tuning for extractive objectives.
Outcome:	The proposed model can extract arguments with the same role instead of heuristic threshold tuning.

Copied to clipboard

Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun

Language Models

Challenge:	SciAgent surpasses other LLMs with the comparable size by more than 8.0% in absolute accuracy.
Approach:	They propose a tool-augmented scientific reasoning setting that supplements LLMs with scalable toolsets and builds a benchmark to evaluate LLM’s abilities with tool assistance.
Outcome:	The proposed setting augments LLMs with scalable toolsets and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user.

Semantic-Eval : A Semantic Comprehension Evaluation Framework for Large Language Models Generation without Training (2025.acl-long)

Copied to clipboard

Shusheng Li, Jiale Li, Yifei Qu, Xinwei Shi, Yanliang Guo, Ziyi He, Yubo Wang, Wenjun Tan

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) have emerged as key drivers of progress in the field of natural language processing.
Approach:	They propose a framework that assesses LLM-generated text based on semantic understanding.
Outcome:	The proposed framework surpasses traditional evaluation metrics and lags behind GPT-4.

Copied to clipboard

Yuheng Chen, Pengfei Cao, Yubo Chen, Yining Wang, Shengping Liu, Kang Liu, Jun Zhao

AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)

Challenge:	Large language models (LLMs) are believed to store extensive factual knowledge, yet the mechanisms of knowledge storage in LLMs remain largely unexplored.
Approach:	They propose that some multi-layer perceptron neurons can store "knowledge".
Outcome:	The proposed model can store "knowledge" in multi-layer perceptron neurons, but not redundancy.

Copied to clipboard

Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao

Leros: Learning Explicit Reasoning on Synthesized Data for Commonsense Question Answering (2024.lrec-main)

Challenge:	Recent advances in deep learning have significantly impacted the legal domain.
Approach:	They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base .
Outcome:	The proposed framework outperforms existing methods in various aspects, especially in generating legal articles.

Copied to clipboard

Chenhao Wang, Pengfei Cao, Jiachun Li, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Li Qiuxia, Jun Zhao

Synergistic Weak-Strong Collaboration by Aligning Preferences (2025.acl-long)

Challenge:	Recent work shows large language models can generate useful rationales for commonsense question answering (CQA) however, the cost of deployment and further tuning is relatively expensive for the large models.
Approach:	They propose a framework that leverages both knowledge graphs and large language models to synthesize rationale-augmented CQA data.
Outcome:	The proposed model can generate useful rationales on unseen CQA benchmarks.

Copied to clipboard

Yizhu Jiao, Xuchao Zhang, Zhaoyang Wang, Yubo Ma, Zhun Deng, Rujia Wang, Chetan Bansal, Saravan Rajmohan, Jiawei Han, Huaxiu Yao

Few-shot Event Detection: An Empirical Study and a Unified View (2023.acl-long)

Challenge:	Current Large Language Models excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge.
Approach:	They propose a collaborative framework that pairs a specialized weak model with a general strong model to optimize collaboration.
Outcome:	The proposed framework outperforms each model alone by leveraging complementary strengths.

Copied to clipboard

Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun