Lei Sha

Large Language Models Struggle with Unreasonability in Math Problems AAAI 2026 SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory ACL 2026 DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak EMNLP 2025 How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation ACL 2025 Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025 LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts ACL 2025 Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models ICLR 2025 Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025 Towards Harmonized Uncertainty Estimation for Large Language Models ACL 2025 ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings EMNLP 2024 A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks ICLR 2024 ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator EMNLP 2024 Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024 Harnessing the Plug-and-Play Controller by Prompting EMNLP 2023 RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models AACL 2022 Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning Interspeech 2022 Associative Memories via Predictive Coding NeurIPS 2021 Controlling Text Edition by Changing Answers of Specific Questions ACL 2021 Learning from the Best: Rationalizing Predictions by Adversarial Information Calibration AAAI 2021 Multi-type Disentanglement without Adversarial Training AAAI 2021 Gradient-guided Unsupervised Lexically Constrained Text Generation EMNLP 2020 Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning EMNLP 2018 A Progressive Learning Approach to Chinese SRL Using Heterogeneous Data ACL 2017 Capturing Argument Relationship for Chinese Semantic Role Labeling EMNLP 2016 Encoding Temporal Information for Time-Aware Link Prediction EMNLP 2016 Joint Learning Templates and Slots for Event Schema Induction NAACL 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 Multi-label Text Categorization with Joint Learning Predictions-as-Features Method EMNLP 2015 Recognizing Textual Entailment Using Probabilistic Inference EMNLP 2015