Songlin Hu

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs AAAI 2026 FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs ACL 2026 Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents ACL 2026 More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters ACL 2026 Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective ACL 2026 Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment ACL 2026 An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding AAAI 2025 BotSim: LLM-Powered Malicious Social Botnet Simulation AAAI 2025 Capture the Key in Reasoning to Enhance CoT Distillation Generalization ACL 2025 CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts NAACL 2025 Chain of Attack: Hide Your Intention through Multi-Turn Interrogation ACL 2025 DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent COLING 2025 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 Dynamic Simulation Framework for Disinformation Dissemination and Correction With Social Bots EMNLP 2025 Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models AAAI 2025 Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models EMNLP 2025 Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding ACL 2025 LLM-Based Behavior Prediction for Social Media Users with Continuous Memory IJCNLP 2025 LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing EMNLP 2025 NExtLong: Toward Effective Long-Context Training without Long Documents ICML 2025 Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model ICLR 2025 Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation EMNLP 2025 Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detection ACL 2025 Structure-aware Propagation Generation with Large Language Models for Fake News Detection EMNLP 2025 Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval AAAI 2025 Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems NAACL 2024 Few-Shot Learning for Cold-Start Recommendation COLING 2024 Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction EMNLP 2024 Improve Student’s Reasoning Generalizability through Cascading Decomposed CoTs Distillation EMNLP 2024 MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models NAACL 2024 Multi-stream Information Fusion Framework for Emotional Support Conversation COLING 2024 Representation Learning with Conditional Information Flow Maximization ACL 2024 Structured Probabilistic Coding AAAI 2024 Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection COLING 2024 Uncertainty-Guided Modal Rebalance for Hateful Memes Detection ACL 2024 ConTextual Masked Auto-Encoder for Dense Passage Retrieval AAAI 2023 CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability EMNLP 2023 PUNR: Pre-training with User Behavior Modeling for News Recommendation EMNLP 2023 QAP: A Quantum-Inspired Adaptive-Priority-Learning Model for Multimodal Emotion Recognition ACL 2023 Query-as-context Pre-training for Dense Passage Retrieval EMNLP 2023 Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations ACL 2023 TrojanSQL: SQL Injection against Natural Language Interface to Database EMNLP 2023 UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis SemEval 2023 AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis COLING 2022 A Unified Propagation Forest-based Framework for Fake News Detection COLING 2022 ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding COLING 2022 InfoCSE: Information-aggregated Contrastive Learning of Sentence Embeddings EMNLP 2022 Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion Cause Pair Extraction ACL 2022 RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval EMNLP 2022 Smoothed Contrastive Learning for Unsupervised Sentence Embedding COLING 2022 Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in Conversation IJCAI 2022 Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation EMNLP 2022 Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks ACL 2022 Uncertainty-aware Propagation Structure Reconstruction for Fake News Detection COLING 2022 An Adaptive Hybrid Framework for Cross-domain Aspect-based Sentiment Analysis AAAI 2021 Label-Specific Dual Graph Neural Network for Multi-Label Text Classification ACL 2021 Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection ACL 2021 Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning COLING 2020 Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering AAAI 2020 Integrating External Event Knowledge for Script Learning COLING 2020 Symmetric Metric Learning with Adaptive Margin for Recommendation AAAI 2020 Who Are Controlled by The Same User? Multiple Identities Deception Detection via Social Interaction Activity (Student Abstract) AAAI 2020 A Fuzzy Set Based Approach for Rating Bias AAAI 2019 A Span-based Joint Model for Opinion Target Extraction and Target Sentiment Classification IJCAI 2019 Mask and Infill: Applying Masked Language Model for Sentiment Transfer IJCAI 2019 Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots EMNLP 2019 SAM-Net: Integrating Event-Level and Chain-Level Attentions to Predict What Happens Next AAAI 2019