Papers by Yongliang Shen

Leveraging Outline-Optimized Generative Interactions and Critique for Self-Refining Outlines with Reinforcement Learning (2026.acl-long)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Hengwei Liu, Haoyuan Ma, Qingqing Lyu, Daoxin Zhang, Yao Hu, Yongliang Shen, Yin Zhang, Weiming Lu

Challenge:	Logic-RL is a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning.
Approach:	They propose a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning.
Outcome:	The proposed framework improves on FreshWiki and WikiOutline . it can be iteratively applied, with improved quality continuing through three refinement rounds before diminishing returns.

Enhancing Emotion Recognition in Conversation via Multi-view Feature Alignment and Memorization (2023.findings-emnlp)

Copied to clipboard

Guiyang Hou, Yongliang Shen, Wenqi Zhang, Wei Xue, Weiming Lu

Multimodality

Challenge:	Emotion recognition in conversation (ERC) is an advanced capability of conversational AI systems.
Approach:	They propose a semi-parametric paradigm for Emotion Recognition in conversation that uses supervised contrastive learning to align semantic-view and context-view features.
Outcome:	The proposed model achieves state-of-the-art on four widely used benchmarks.

Advancing Process Verification for Large Language Models via Tree-Based Preference Learning (2024.emnlp-main)

Copied to clipboard

Mingqian He, Yongliang Shen, Wenqi Zhang, Zeqi Tan, Weiming Lu

ToM-Synth: Scaling Robust Theory of Mind in LLMs via 6,912 Structured Social Units (2026.findings-acl)

Challenge:	Existing methods for generating step-by-step rationales fail to fully utilize the relative merits of intermediate steps, limiting the effectiveness of feedback provided.
Approach:	They propose a tree-based preference learning verifier that constructs reasoning trees via a best-first search algorithm and collects step-level paired data for preference training.
Outcome:	The proposed approach outperforms existing benchmarks on arithmetic and commonsense reasoning tasks.

Copied to clipboard

Guiyang Hou, Xiang Huang, Shangke Lyu, Yuchuan Wu, Weiyao Luo, Xinyu Mei, Yongliang Shen, Weiming Lu, Yongbin Li

Robustness in NLP

Challenge:	Existing methods endowing LLMs with Theory of Mind fail to internalize the augmented ToM into the LLM.
Approach:	They propose a factorial combinatorial synthesis framework that enables systematic synthesis of ToM data and uses it for RL fine-tuning.
Outcome:	The proposed framework yields a training dataset of 27,648 instances.

Insert or Attach: Taxonomy Completion via Box Embedding (2024.acl-long)

Copied to clipboard

Wei Xue, Yongliang Shen, Wenqi Ren, Jietian Guo, Shiliang Pu, Weiming Lu

Representation Learning

Challenge:	Existing taxonomy expansion methods embed concepts as vectors in Euclidean space, causing incorrectly model asymmetric relations.
Approach:	They propose to use box containment and center closeness to create geometric scorers that capture intrinsic relationships between concepts.
Outcome:	The proposed framework outperforms existing methods on four real-world datasets.

Logic: Long-form Outline Generation via Imitative and Critical Self-refinement (2025.findings-emnlp)

Copied to clipboard

Hengwei Liu, Yongliang Shen, Zhe Zheng, Haoyuan Ma, Xingyu Wu, Yin Zhang, Weiming Lu

Information Retrieval

Challenge:	Existing methods for long-form outline generation have low knowledge density and lack detail . retrieval-augmented approaches struggle to maintain logical coherence across retrieved information .
Approach:	They propose a system that mimics human writers' refinement process by mimicking outlines through imitation and critical self-refinement.
Outcome:	The proposed system improves on the FreshWiki and WikiOutline datasets and establishes a coherent planning framework and structured knowledge base.

Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization (2024.acl-long)

Copied to clipboard

Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, Weiming Lu

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) are designed as specific task solvers with sophisticated prompt engineering, but are inherently incapacitating to address complex dynamic scenarios.
Approach:	They propose an LLM-based agent with policy-level reflection and optimization that can learn from interactive experiences and progressively elevate its behavioral policy.
Outcome:	The proposed agent outperforms vanilla LLM and specialized models in blackjack and Texas hold’em.

Copied to clipboard

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

Responsible & Trustworthy NLP

Challenge:	Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach:	They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome:	The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.

A Set Prediction Network For Extractive Summarization (2023.findings-acl)

Copied to clipboard

Xiaoxia Cheng, Yongliang Shen, Weiming Lu

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Recent approaches to extracting salient sentences from source document are naive and lack dependencies between sentences.
Approach:	They propose a set prediction network to detect redundancy relationship between sentences . they use a non-autoregressive decoder to predict sentences in parallel .
Outcome:	The proposed method outperforms previous state-of-the-art models on extracted summary datasets.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

MProto: Multi-Prototype Network with Denoised Optimal Transport for Distantly Supervised Named Entity Recognition (2023.emnlp-main)

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Copied to clipboard

Shuhui Wu, Yongliang Shen, Zeqi Tan, Wenqi Ren, Jietian Guo, Shiliang Pu, Weiming Lu

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Challenge:	Distantly supervised named entity recognition (DS-NER) aims to locate entity mentions and classify their types with knowledge bases or gazetteers and unlabeled corpus.
Approach:	They propose a noise-robust prototype network named MProto for a DS-NER task . they propose an optimal transport algorithm to mitigate the noise from incomplete labeling .
Outcome:	The proposed network achieves state-of-the-art on several DS-NER benchmarks.

Copied to clipboard

Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang, Hui Xue, Yongliang Shen, Weiming Lu, Yueting Zhuang

Multimodality

Challenge:	Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach:	They propose a routing-guided intervention method that enhances domain expert activation.
Outcome:	The proposed method achieves consistent improvements on visual reasoning tasks.

Scaling LLMs’ Social Reasoning: Sprinkle Cognitive “Aha Moment” into Fundamental Long-thought Logical Capabilities (2025.findings-acl)

Copied to clipboard

Guiyang Hou, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Weiming Lu

Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem (2022.findings-emnlp)

Challenge:	Existing studies have examined how large language models’ social reasoning capabilities evolve during model size scaling or reasoning tokens scaling.
Approach:	They propose to optimize evaluation of Large Language Models from both data and model perspectives and to analyze their reasoning trajectories to identify notable cognitive "Aha Moments"
Outcome:	The proposed model outperforms the o1-preview model by 19.0 points in the evaluation of large language models.

Copied to clipboard

Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, Weiming Lu

De-Bias for Generative Extraction in Unified NER Task (2022.acl-long)

Challenge:	Existing methods for generating complex semantics and diverse equations are limited by a fixed view.
Approach:	They propose a multi-view consistent contrastive learning approach that decouples human reasoning into two independent but consistent views.
Outcome:	The proposed approach significantly outperforms existing baselines on complex problems on multiple languages.

Copied to clipboard

Shuai Zhang, Yongliang Shen, Zeqi Tan, Yiquan Wu, Weiming Lu

UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)

Challenge:	Existing methods for Named entity recognition (NER) are not consistent with the task, which makes the model vulnerable to incorrect biases.
Approach:	They propose to use generative model to recognize entities from sentences . they analyze incorrect biases in the generation process from a causal perspective .
Outcome:	The proposed method improves the performance of the generative NER model in various datasets.

Copied to clipboard

Zhengxi Lu, Fei Tang, Guangyi Liu, Jin Ma, Kaitao Song, Xu Tan, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

Information Retrieval

Challenge:	Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B.
Approach:	They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation.
Outcome:	The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model.

An Expression Tree Decoding Strategy for Mathematical Equation Generation (2023.emnlp-main)

Copied to clipboard

Wenqi Zhang, Yongliang Shen, Qingpeng Nong, Zeqi Tan, Yanna Ma, Weiming Lu

Learning Global Controller in Latent Space for Parameter-Efficient Fine-Tuning (2024.acl-long)

Challenge:	Existing approaches to generate mathematical equations from natural language ignore parallel or dependent relations between math expressions.
Approach:	They propose to integrate tree structure into the expression-level generation and advocate an expression tree decoding strategy.
Outcome:	The proposed method outperforms baseline methods for generating mathematical equations from natural language.

Copied to clipboard

Zeqi Tan, Yongliang Shen, Xiaoxia Cheng, Chang Zong, Wenqi Zhang, Jian Shao, Weiming Lu, Yueting Zhuang

Green & Sustainable NLP

Challenge:	Large language models (LLMs) have shown remarkable performance, but their training costs are exorbitant.
Approach:	They propose a parameter-efficient method for exploring optimal solutions within latent space by using latent units to extract input representations from LLMs.
Outcome:	The proposed method improves performance on a range of natural language processing tasks.

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities (2026.acl-long)

Copied to clipboard

Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen, Guozhou Zheng, Huajun Chen, Shumin Deng

Query-based Instance Discrimination Network for Relational Triple Extraction (2022.emnlp-main)

Challenge:	Large language models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors pose significant risks.
Approach:	They propose a hierarchical benchmark for evaluating LLM controllability across three domains: language features, sentiment, and personality.
Outcome:	The proposed framework offers a principled and interpretable framework for safe and controllable LLM behavior serving as a foundation for future research.

Copied to clipboard

Zeqi Tan, Yongliang Shen, Xuming Hu, Wenqi Zhang, Xiaoxia Cheng, Weiming Lu, Yueting Zhuang

STaR-SQL: Self-Taught Reasoner for Text-to-SQL (2025.acl-long)

Challenge:	Recent approaches to extract relational triples from open domain texts suffer from error propagation, relation redundancy and lack of high-level connections.
Approach:	They propose a query-based approach to construct instance-level representations for relational triples . they use query embeddings and token embeddables to extract all types of triples in one step .
Outcome:	The proposed method achieves state-of-the-art on five widely used benchmarks.

Copied to clipboard

Mingqian He, Yongliang Shen, Wenqi Zhang, Qiuying Peng, Jun Wang, Weiming Lu

Programming Languages in NLP

Challenge:	Existing methods for generating step-by-step “chain-of-thought” rationales are limited to text-to-SQL.
Approach:	They propose a method that prompts SQL query generation to produce reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes.
Outcome:	The proposed method outperforms agent-like prompting methods on the Spider benchmark.

DiffusionNER: Boundary Diffusion for Named Entity Recognition (2023.acl-long)

Copied to clipboard

Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

PromptNER: Prompt Locating and Typing for Named Entity Recognition (2023.acl-long)

Challenge:	Named Entity Recognition (NER) tasks are fundamental to many structured information extraction tasks.
Approach:	They propose a named entity recognition task that uses a boundary-denoising diffusion process to denoise noisy spans.
Outcome:	The proposed method achieves comparable or even better performance than previous state-of-the-art models on flat and nested datasets.

Copied to clipboard

Yongliang Shen, Zeqi Tan, Shuhui Wu, Wenqi Zhang, Rongsheng Zhang, Yadong Xi, Weiming Lu, Yueting Zhuang

Low-Resource NLP

Challenge:	Existing methods for prompt learning require a multi-round prompting manner and require elaborate templates.
Approach:	They propose to unify entity locating and entity typing into prompt learning by enumerating spans to predict their entity types or constructing type-specific prompts to locate entities.
Outcome:	The proposed model outperforms the state-of-the-art model in a few-shot setting . it uses a template filled with multiple prompts and a bipartite graph matching mechanism .

EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction (2025.naacl-long)

Copied to clipboard

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Kan Ren, Dongsheng Li, Deqing Yang

Parallel Instance Query Network for Named Entity Recognition (2022.acl-long)

Challenge:	EASYTOOL combines tools from diverse tool documentation into a single tool instruction.
Approach:	They propose a framework that transforms tool documentation into a unified tool instruction.
Outcome:	EASYTOOL combines extensive tool documentation into a concise tool instruction . it reduces token consumption and improves performance of LLM-based agents .

Copied to clipboard

Yongliang Shen, Xiaobin Wang, Zeqi Tan, Guangwei Xu, Pengjun Xie, Fei Huang, Weiming Lu, Yueting Zhuang

Knowledge Representation

Challenge:	Named entity recognition is a fundamental task in natural language processing.
Approach:	They propose a method that sets up global and learnable instance queries to extract entities from a sentence in a parallel manner.
Outcome:	The proposed method outperforms existing state-of-the-art models on nested and flat datasets.

Minimally-Supervised Relation Induction from Pre-trained Language Model (2022.findings-naacl)

Copied to clipboard

Lu Sun, Yongliang Shen, Weiming Lu

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives (2024.acl-long)

Challenge:	Existing methods to induce relation in NLP depend heavily on word embeddings.
Approach:	They propose a method to induce relation with BERT under minimal supervision . they first extract proper templates from corpus and then use BERT attention weights to represent the pseudo-sentences.
Outcome:	The proposed method achieves state-of-the-art in relation induction tasks on Google Analogy Test Sets, Bigger Analogy test set (BATS) and DiffVec.

Copied to clipboard

Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese (2026.acl-long)

Challenge:	Recent research indicates without external feedback, LLM’s intrinsic reflection is unstable.
Approach:	They propose a method that combines self-evaluated and external feedback to improve LLM's reflection.
Outcome:	The proposed method improves the quality of self-evaluated feedback and can catalyze more accurate and stable reflection.

Copied to clipboard

Xing Yue, Yongliang Shen, Weiming Lu

Syntactic Text Processing

Challenge:	Existing benchmarks on LLMs’ phonological abilities are either solvable through rote memorization or intertwined with other abilities, making them inadequate to measure LLM’s genuine ability in phonological understanding.
Approach:	They propose to use a Chinese benchmark to evaluate LLMs' phonological understanding to test their ability to recall correct pronunciations.
Outcome:	The proposed benchmarks show that LLMs excel at recalling correct pronunciations, but struggle to leverage phonological knowledge in the flexible and intuitive way that human speakers do.

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition (2021.acl-long)

Copied to clipboard

Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Challenge:	Named entity recognition (NER) is a well-studied task in natural language processing.
Approach:	They propose a method that generates span proposals and labels them with categories . they use boundary information of entities and partially matched spans to locate them .
Outcome:	The proposed method outperforms state-of-the-art models on nested NER datasets.

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs (2026.acl-long)

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

Copied to clipboard

Qingqing Lyu, Linjuan Wu, Yongliang Shen, Hengwei Liu, Hao Li, Shengpei Jiang, Yin Zhang, Weiming Lu

Challenge:	Existing automated approaches operate within fixed task schemas and often fail to autonomously discover new evaluation dimensions.
Approach:	They propose an automated framework that constructs domain-specific benchmarks directly from unstructured corpora using Bloom’s Taxonomy.
Outcome:	The proposed framework uncovers a broader and more fine-grained task space than expert-curated benchmarks while producing high-quality instances that preserve established model-level evaluation trends.

TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models’ Theory-of-Mind (2024.findings-acl)

Copied to clipboard

Guiyang Hou, Wenqi Zhang, Yongliang Shen, Linjuan Wu, Weiming Lu