Shumin Deng

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities ACL 2026 Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency ACL 2026 StructMem: Structured Memory for Long-Horizon Behavior in LLMs ACL 2026 KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks AAAI 2026 Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics ACL 2026 DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation COLING 2025 Exploring Model Kinship for Merging Large Language Models EMNLP 2025 CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners EMNLP 2025 ReLearn: Unlearning via Learning for Large Language Models ACL 2025 ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging. SEMEVAL 2025 KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2025 FlipAttack: Jailbreak LLMs via Flipping ICML 2025 MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation ICLR 2025 Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms ACL 2025 How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training ACL 2025 ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging. ACL 2025 Automating Steering for Safe Multimodal Large Language Models EMNLP 2025 Detoxifying Large Language Models via Knowledge Editing ACL 2024 Agent Planning with World Knowledge Model NIPS 2024 Knowledge Circuits in Pretrained Transformers NIPS 2024 When Do Program-of-Thought Works for Reasoning? AAAI 2024 Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View ACL 2024 Towards A Unified View of Answer Calibration for Multi-Step Reasoning ACL 2024 Knowledge Editing for Large Language Models COLING 2024 Editing Conceptual Knowledge for Large Language Models EMNLP 2024 Knowledge Mechanisms in Large Language Models: A Survey and Perspective EMNLP 2024 Editing Large Language Models: Problems, Methods, and Opportunities EMNLP 2023 From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal ICCV 2023 Reasoning with Language Model Prompting: A Survey ACL 2023 Editing Large Language Models IJCNLP 2023 Multimodal Analogical Reasoning over Knowledge Graphs ICLR 2023 SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres ACL 2023 Editing Large Language Models AACL 2023 Learning to Ask for Data-Efficient Event Argument Extraction (Student Abstract) AAAI 2022 Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning NIPS 2022 LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting COLING 2022 Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction NAACL 2022 Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners ICLR 2022 OntoProtein: Protein Pretraining With Gene Ontology Embedding ICLR 2022 Molecular Contrastive Learning with Chemical Element Knowledge Graph AAAI 2022 ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning SEMEVAL 2021 Contrastive Triple Extraction with Generative Transformer AAAI 2021 ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning ACL 2021 Document-level Relation Extraction as Semantic Segmentation IJCAI 2021 Drop Redundant, Shrink Irrelevant: Selective Knowledge Injection for Language Pretraining IJCAI 2021 OntoED: Low-resource Event Detection with Ontology Embedding IJCNLP 2021 MLBiNet: A Cross-Sentence Collective Event Detection Network IJCNLP 2021 ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning IJCNLP 2021 MLBiNet: A Cross-Sentence Collective Event Detection Network ACL 2021 OntoED: Low-resource Event Detection with Ontology Embedding ACL 2021 OpenUE: An Open Toolkit of Universal Extraction from Text EMNLP 2020 Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention EMNLP 2020 When Low Resource NLP Meets Unsupervised Language Model: Meta-Pretraining then Meta-Learning for Few-Shot Text Classification (Student Abstract) AAAI 2020 Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction COLING 2020 Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks NAACL 2019 Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction EMNLP 2018