Zhifang Sui

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling AAAI 2026 GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation CVPR 2026 HistLens: Mapping Idea Change across Concepts and Corpora ACL 2026 Large Language Models Struggle with Unreasonability in Math Problems AAAI 2026 RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection AAAI 2026 Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts ACL 2026 AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization CVPR 2025 A Probabilistic Inference Scaling Theory for LLM Self-Correction EMNLP 2025 Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? EMNLP 2025 Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs ACL 2025 Exploring Activation Patterns of Parameters in Language Models AAAI 2025 How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation ACL 2025 Language Models Encode the Value of Numbers Linearly COLING 2025 Self-Boosting Large Language Models with Synthetic Preference Data ICLR 2025 SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine NAACL 2025 Towards Harmonized Uncertainty Estimation for Large Language Models ACL 2025 Achilles-Bench: A Challenging Benchmark for Low-Resource Evaluation ACL 2024 A Survey on In-context Learning EMNLP 2024 Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024 Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? EMNLP 2024 Can Large Multimodal Models Uncover Deep Semantics Behind Images? ACL 2024 DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models ACL 2024 FaGANet: An Evidence-Based Fact-Checking Model with Integrated Encoder Leveraging Contextual Information COLING 2024 Large Language Models are not Fair Evaluators ACL 2024 Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations ACL 2024 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024 Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens EMNLP 2024 Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding ACL 2024 Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization EMNLP 2023 Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion ACL 2023 DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog EMNLP 2023 Enhancing Continual Relation Extraction via Classifier Decomposition ACL 2023 Guiding AMR Parsing with Reverse Graph Linearization EMNLP 2023 ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories EMNLP 2023 InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective EMNLP 2023 Learn to Not Link: Exploring NIL Prediction in Entity Linking ACL 2023 Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning EMNLP 2023 Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation EMNLP 2023 Statistical Knowledge Assessment for Large Language Models NeurIPS 2023 Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers ACL 2023 An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling NAACL 2022 A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation ACL 2022 ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs NAACL 2022 A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction NAACL 2022 Calibrating Factual Knowledge in Pretrained Language Models EMNLP 2022 CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark ACL 2022 DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection EMNLP 2022 Hierarchical Curriculum Learning for AMR Parsing ACL 2022 HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification EMNLP 2022 Knowledge Neurons in Pretrained Transformers ACL 2022 Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation EMNLP 2022 Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues ACL 2022 Robust Fine-tuning via Perturbation and Interpolation from In-batch Instances IJCAI 2022 StableMoE: Stable Routing Strategy for Mixture of Experts ACL 2022 Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation NAACL 2021 Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions ACL 2021 Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View AAAI 2021 An Anchor-Based Automatic Evaluation Metric for Document Summarization COLING 2020 An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference CoNLL 2020 A Spectral Method for Unsupervised Multi-Document Summarization EMNLP 2020 Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference EMNLP 2020 A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer IJCAI 2019 Hierarchical Encoder with Auxiliary Supervision for Neural Table-to-Text Generation: Learning Better Representation for Tables AAAI 2019 Learning to Control the Fine-grained Sentiment for Story Ending Generation ACL 2019 Pun-GAN: Generative Adversarial Network for Pun Generation EMNLP 2019 Towards Comprehensive Description Generation from Factual Attribute-value Tables ACL 2019 Towards Fine-grained Text Sentiment Transfer ACL 2019 WSD-GAN: Word Sense Disambiguation Using Generative Adversarial Networks AAAI 2019 Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition EMNLP 2018 Incorporating Glosses into Neural Word Sense Disambiguation ACL 2018 Leveraging Gloss Knowledge in Neural Word Sense Disambiguation by Hierarchical Co-Attention EMNLP 2018 Affinity-Preserving Random Walk for Multi-Document Summarization EMNLP 2017 A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data ACL 2017 A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction EMNLP 2017 Capturing Argument Relationship for Chinese Semantic Role Labeling EMNLP 2016 Encoding Temporal Information for Time-Aware Link Prediction EMNLP 2016 Event Detection with Burst Information Networks COLING 2016 Joint Learning Templates and Slots for Event Schema Induction NAACL 2016 News Stream Summarization using Burst Information Networks EMNLP 2016 RBPB: Regularization-Based Pattern Balancing Method for Event Extraction ACL 2016 Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition COLING 2016 Towards Time-Aware Knowledge Graph Completion COLING 2016 An Ontology Matching Approach Based on Affinity-Preserving Random Walks IJCAI 2015 Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles ACL 2015 Chinese Semantic Role Labeling with Bidirectional Recurrent Neural Networks EMNLP 2015 ERSOM: A Structural Ontology Matching Approach Using Automatically Learned Entity Representation EMNLP 2015 One Tense per Scene: Predicting Tense in Chinese Conversations ACL 2015 Recognizing Textual Entailment Using Probabilistic Inference EMNLP 2015 Event-Based Time Label Propagation for Automatic Dating of News Articles EMNLP 2013 Towards Accurate Distant Supervision for Relational Facts Extraction ACL 2013 Fine-Grained Classification of Named Entities by Fusing Multi-Features COLING 2012 Chinese Semantic Role Labeling with Shallow Parsing EMNLP 2009 Prediction of Thematic Rank for Structured Semantic Role Labeling ACL 2009 Prediction of Maximal Projection for Semantic Role Labeling COLING 2008 The Integration of Dependency Relation Classification and Semantic Role Labeling Using Bilayer Maximum Entropy Markov Models CoNLL 2008 Domain Knowledge Engineering Based on Encyclopedias and the Web Text IJCNLP 2005 An Information-Theory-Based Feature Type Analysis for the Modeling of Statistical Parsing ACL 2000