Liwei Jiang

AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text ICLR 2025 Can Language Models Reason about Individualistic Human Values and Preferences? ACL 2025 CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs’ Cultural Knowledge Through Human-AI Red-Teaming ACL 2025 DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life ICLR 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 Online Covariance Estimation in Nonsmooth Stochastic Approximation COLT 2025 Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It ICML 2025 SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior ICML 2025 To Err Is AI: A Case Study Informing LLM Flaw Reporting Practices AAAI 2025 Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL 2024 JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL 2024 Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement ICLR 2024 Position: A Roadmap to Pluralistic Alignment ICML 2024 The Generative AI Paradox: “What It Can Create, It May Not Understand” ICLR 2024 Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties AAAI 2024 WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs NeurIPS 2024 WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models NeurIPS 2024 BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases EMNLP 2023 ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations ACL 2023 Faith and Fate: Limits of Transformers on Compositionality NeurIPS 2023 Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP 2023 NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation EMNLP 2023 Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms EMNLP 2023 SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization EMNLP 2023 What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations EMNLP 2023 Aligning to Social Norms and Values in Interactive Narratives NAACL 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 Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022 “I’m Not Mad”: Commonsense Implications of Negation and Contradiction NAACL 2021 Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery NeurIPS 2021