Yanjun Qi

Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL Estimator AAAI 2026 The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems EACL 2026 AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning ACL 2025 Augmented Adversarial Trigger Learning NAACL 2025 DFLOW: Diverse Dialogue Flow Simulation with Large Language Models ACL 2025 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation EMNLP 2025 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt. Generation for Enhanced LLM Content Moderation ACL 2025 TaeBench: Improving Quality of Toxic Adversarial Examples NAACL 2025 TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice NAACL 2025 Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency EMNLP 2025 LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning EMNLP 2024 Less is More for Improving Automatic Evaluation of Factual Consistency NAACL 2024 Expanding Scope: Adapting English Adversarial Attacks to Chinese ACL 2023 Improving Interpretability via Explicit Word Interaction Graph Layer AAAI 2023 PGrad: Learning Principal Gradients For Domain Generalization ICLR 2023 Towards Building a Robust Toxicity Predictor ACL 2023 Beyond Data Samples: Aligning Differential Networks Estimation with Scientific Knowledge AISTATS 2022 ST-MAML : A stochastic-task based method for task-heterogeneous meta-learning UAI 2022 White-box Testing of NLP models with Mask Neuron Coverage NAACL 2022 Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning AAAI 2021 General Multi-Label Image Classification With Transformers CVPR 2021 Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing EMNLP 2021 Towards Improving Adversarial Training of NLP Models EMNLP 2021 Reevaluating Adversarial Examples in Natural Language EMNLP 2020 Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples EMNLP 2020 TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP EMNLP 2020 TextAttack: Lessons learned in designing Python frameworks for NLP EMNLP 2020 A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models ICML 2018 Fast and Scalable Learning of Sparse Changes in High-Dimensional Gaussian Graphical Model Structure AISTATS 2018 A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Models AISTATS 2017 Attend and Predict: Understanding Gene Regulation by Selective Attention on Chromatin NeurIPS 2017 Learning the Dependency Structure of Latent Factors NeurIPS 2012 Polynomial Semantic Indexing NeurIPS 2009