Hongning Wang

Data Efficient RLVR via Off-Policy Influence Guidance ACL 2026 Glyph: Scaling Context Windows via Visual-Text Compression ACL 2026 How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study ACL 2026 HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing ACL 2026 IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation ACL 2026 IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation ACL 2026 LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ACL 2026 When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026 CharacterBench: Benchmarking Character Customization of Large Language Models AAAI 2025 CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning ICLR 2025 Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues EMNLP 2025 Data Selection via Optimal Control for Language Models ICLR 2025 Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025 HPSS: Heuristic Prompting Strategy Search for LLM Evaluators ACL 2025 LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models ACL 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 MAPS: Advancing Multi-Modal Reasoning in Expert-Level Physical Science ICLR 2025 RecFlow: An Industrial Full Flow Recommendation Dataset ICLR 2025 SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation EMNLP 2025 SocialEval: Evaluating Social Intelligence of Large Language Models ACL 2025 SocialSim: Towards Socialized Simulation of Emotional Support Conversation AAAI 2025 SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models ICLR 2025 Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains ACL 2025 VPO: Aligning Text-to-Video Generation Models with Prompt Optimization ICCV 2025 AlignBench: Benchmarking Chinese Alignment of Large Language Models ACL 2024 AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback NeurIPS 2024 AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models EMNLP 2024 Benchmarking Complex Instruction-Following with Multiple Constraints Composition NeurIPS 2024 Black-Box Prompt Optimization: Aligning Large Language Models without Model Training ACL 2024 CharacterGLM: Customizing Social Characters with Large Language Models EMNLP 2024 CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation ACL 2024 Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization ACL 2024 Federated Linear Contextual Bandits with Heterogeneous Clients AISTATS 2024 Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict? ICML 2024 Incentivized Truthful Communication for Federated Bandits ICLR 2024 Language Model Decoding as Direct Metrics Optimization ICLR 2024 Learning Task Decomposition to Assist Humans in Competitive Programming ACL 2024 Meta-Reinforcement Learning via Exploratory Task Clustering AAAI 2024 Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NeurIPS 2024 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024 Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits AAAI 2024 Towards Efficient Exact Optimization of Language Model Alignment ICML 2024 Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms NeurIPS 2024 COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation EMNLP 2023 How Bad is Top-K Recommendation under Competing Content Creators? ICML 2023 Incentivized Communication for Federated Bandits NeurIPS 2023 Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment ICLR 2023 Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems NeurIPS 2023 Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial? NeurIPS 2023 Spectral Augmentation for Self-Supervised Learning on Graphs ICLR 2023 Uncertainty-Aware Instance Reweighting for Off-Policy Learning NeurIPS 2023 Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits AISTATS 2022 Communication Efficient Distributed Learning for Kernelized Contextual Bandits NeurIPS 2022 Communication Efficient Federated Learning for Generalized Linear Bandits NeurIPS 2022 IMO^3: Interactive Multi-Objective Off-Policy Optimization IJCAI 2022 Learning from a Learning User for Optimal Recommendations ICML 2022 Learning Neural Contextual Bandits through Perturbed Rewards ICLR 2022 Learning the Optimal Recommendation from Explorative Users AAAI 2022 When Are Linear Stochastic Bandits Attackable? ICML 2022 Learning from Crowds by Modeling Common Confusions AAAI 2021 Unifying Clustered and Non-stationary Bandits AISTATS 2021 Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning AAAI 2020 Adversarial Domain Adaptation for Machine Reading Comprehension EMNLP 2019 A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation NeurIPS 2019 Bandit Learning with Implicit Feedback NeurIPS 2018 Multi-Task Learning for Document Ranking and Query Suggestion ICLR 2018 Modeling Social Norms Evolution for Personalized Sentiment Classification ACL 2016 Model Adaptation for Personalized Opinion Analysis ACL 2015 Structural Topic Model for Latent Topical Structure Analysis ACL 2011 Exploiting Structured Ontology to Organize Scattered Online Opinions COLING 2010