Ximing Lu

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text ICLR 2025 Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation ICCV 2025 CertainlyUncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness ICLR 2025 Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models NAACL 2025 Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions EMNLP 2025 Synthetic Visual Genome CVPR 2025 How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models EMNLP 2024 Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL 2024 In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search EMNLP 2024 JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL 2024 Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models ICLR 2024 Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement ICLR 2024 Position: A Roadmap to Pluralistic Alignment ICML 2024 StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements EMNLP 2024 Tailoring Self-Rationalizers with Multi-Reward Distillation ICLR 2024 The Generative AI Paradox: “What It Can Create, It May Not Understand” ICLR 2024 The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning ICLR 2024 Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties AAAI 2024 WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models NeurIPS 2024 ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations ACL 2023 Faith and Fate: Limits of Transformers on Compositionality NeurIPS 2023 Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning CVPR 2023 Generating Sequences by Learning to Self-Correct ICLR 2023 I2D2: Inductive Knowledge Distillation with NeuroLogic and Self-Imitation ACL 2023 Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP 2023 Localized Symbolic Knowledge Distillation for Visual Commonsense Models NeurIPS 2023 NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation EMNLP 2023 SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization EMNLP 2023 STEER: Unified Style Transfer with Expert Reinforcement EMNLP 2023 Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer NAACL 2022 Generated Knowledge Prompting for Commonsense Reasoning ACL 2022 MERLOT Reserve: Neural Script Knowledge Through Vision and Language and Sound CVPR 2022 NaturalProver: Grounded Mathematical Proof Generation with Language Models NeurIPS 2022 NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics NAACL 2022 ProsocialDialog: A Prosocial Backbone for Conversational Agents EMNLP 2022 QUARK: Controllable Text Generation with Reinforced Unlearning NeurIPS 2022 Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering EMNLP 2022 Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022 Twist Decoding: Diverse Generators Guide Each Other EMNLP 2022 DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts ACL 2021 MERLOT: Multimodal Neural Script Knowledge Models NeurIPS 2021 NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints NAACL 2021 On-the-Fly Attention Modulation for Neural Generation ACL 2021 Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models ACL 2021