Liang Pang

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification ACL 2026 RLKD: Distilling LLMs’ Reasoning via Reinforcement Learning AAAI 2026 Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation ACL 2026 The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis ACL 2026 A Theory for Token-Level Harmonization in Retrieval-Augmented Generation ICLR 2025 Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation ICLR 2025 Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models ICLR 2025 Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation COLING 2025 Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models ICLR 2025 Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment EMNLP 2025 LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph AAAI 2025 MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models AAAI 2025 Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations EMNLP 2025 MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models COLING 2025 Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents ICLR 2025 ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models ACL 2025 A Study of Implicit Ranking Unfairness in Large Language Models EMNLP 2024 Beyond Memorization: The Challenge of Random Memory Access in Language Models ACL 2024 Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration ACL 2024 Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration EMNLP 2024 HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data CVPR 2024 Plot Retrieval as an Assessment of Abstract Semantic Association 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 Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation ACL 2024 A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue Generation AAAI 2023 BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval ACL 2023 LLMDet: A Third Party Large Language Models Generated Text Detection Tool EMNLP 2023 MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space EMNLP 2023 Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation EMNLP 2023 RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling EMNLP 2023 SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation ACL 2023 Optimal Partial Transport Based Sentence Selection for Long-form Document Matching COLING 2022 Adaptive Information Seeking for Open-Domain Question Answering EMNLP 2021 Sketch and Customize: A Counterfactual Story Generator AAAI 2021 Transductive Learning for Unsupervised Text Style Transfer EMNLP 2021 Transformation Driven Visual Reasoning CVPR 2021 Uncertainty Calibration for Ensemble-Based Debiasing Methods NeurIPS 2021 Beyond Language: Learning Commonsense from Images for Reasoning EMNLP 2020 Evaluating Natural Language Generation via Unbalanced Optimal Transport IJCAI 2020 METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis COLING 2020 Modeling Topical Relevance for Multi-Turn Dialogue Generation IJCAI 2020 PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation COLING 2020 Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains EMNLP 2020 HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering AAAI 2019 ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation ACL 2019 Locally Smoothed Neural Networks ACML 2017 Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN IJCAI 2016