Huawei Shen

RLKD: Distilling LLMs’ Reasoning via Reinforcement Learning AAAI 2026 Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification ACL 2026 Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization ACL 2026 The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis ACL 2026 HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation ACL 2026 Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents ACL 2026 AuditAgent: LLM Agent for Risks Auditing in Recommender Systems AAAI 2026 PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 The Mirage of Model Editing: Revisiting Evaluation in the Wild ACL 2025 ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models ACL 2025 From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment ACL 2025 Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector ACL 2025 MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models COLING 2025 Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation COLING 2025 Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models EMNLP 2025 Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs EMNLP 2025 Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment EMNLP 2025 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph EMNLP 2025 Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models ICLR 2025 A Theory for Token-Level Harmonization in Retrieval-Augmented Generation ICLR 2025 Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models ICLR 2025 ALiiCE: Evaluating Positional Fine-grained Citation Generation NAACL 2025 SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025 Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject NAACL 2025 TEA: Test-time Energy Adaptation CVPR 2024 Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration EMNLP 2024 The Fall of ROME: Understanding the Collapse of LLMs in Model Editing EMNLP 2024 PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks EMNLP 2024 Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation NIPS 2024 PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion AAAI 2024 Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models AAAI 2024 Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation ACL 2024 Unlocking the Power of Large Language Models for Entity Alignment ACL 2024 Plot Retrieval as an Assessment of Abstract Semantic Association ACL 2024 When to Trust LLMs: Aligning Confidence with Response Quality ACL 2024 Qsnail: A Questionnaire Dataset for Sequential Question Generation COLING 2024 Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue NAACL 2024 Augmentation-Aware Self-Supervision for Data-Efficient GAN Training NIPS 2023 A Provable Framework of Learning Graph Embeddings via Summarization AAAI 2023 BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval ACL 2023 SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation ACL 2023 ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation EMNLP 2023 LLMDet: A Third Party Large Language Models Generated Text Detection Tool EMNLP 2023 RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling EMNLP 2023 MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space EMNLP 2023 Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases COLING 2022 Conditional GANs with Auxiliary Discriminative Classifier ICML 2022 Self-Supervised GANs with Label Augmentation NIPS 2021 Transductive Learning for Unsupervised Text Style Transfer EMNLP 2021 Adaptive Information Seeking for Open-Domain Question Answering EMNLP 2021 SDGNN: Learning Node Representation for Signed Directed Networks AAAI 2021 Slimmable Generative Adversarial Networks AAAI 2021 AugSplicing: Synchronized Behavior Detection in Streaming Tensors AAAI 2021 Towards Consumer Loan Fraud Detection: Graph Neural Networks with Role-Constrained Conditional Random Field AAAI 2021 Beyond Low-frequency Information in Graph Convolutional Networks AAAI 2021 Graph Wavelet Neural Network ICLR 2019 Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning IJCAI 2019 Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation IJCAI 2018 Learning Concise Representations of Users' Influences through Online Behaviors IJCAI 2017 Cascade Dynamics Modeling with Attention-based Recurrent Neural Network IJCAI 2017 Cross-Domain Recommendation: An Embedding and Mapping Approach IJCAI 2017 Predict Anchor Links across Social Networks via an Embedding Approach IJCAI 2016