{"total":161,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277,"area":null},{"id":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194,"area":"diffusion"},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.08679","title":"COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability","created":"2024-02-13","cited_by_count":175,"area":"safety"},{"id":"2408.08252","title":"Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding","created":"2024-08-15","cited_by_count":136,"area":"diffusion"},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2406.00832","title":"BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling","created":"2024-06-02","cited_by_count":121,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111,"area":null},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90,"area":"alignment"},{"id":"2304.14293","title":"Controlled Text Generation with Natural Language Instructions","created":"2023-04-27","cited_by_count":87,"area":null},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80,"area":null},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"area":null},{"id":"2205.09726","title":"RankGen: Improving Text Generation with Large Ranking Models","created":"2022-05-19","cited_by_count":72,"area":null},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2403.13031","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","created":"2024-03-19","cited_by_count":68,"area":"safety"},{"id":"2410.14923","title":"Imprompter: Tricking LLM Agents into Improper Tool Use","created":"2024-10-19","cited_by_count":68,"area":"agents"},{"id":"2205.12558","title":"Gradient-Based Constrained Sampling from Language Models","created":"2022-05-25","cited_by_count":64,"area":null},{"id":"2404.16369","title":"Don't Say No: Jailbreaking LLM by Suppressing Refusal","created":"2024-04-25","cited_by_count":56,"area":"alignment"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2506.09018","title":"Edit Flows: Flow Matching with Edit Operations","created":"2025-06-10","cited_by_count":55,"area":"diffusion"},{"id":"2405.21047","title":"Grammar-Aligned Decoding","created":"2024-05-31","cited_by_count":54,"area":null},{"id":"2504.13139","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","created":"2025-04-17","cited_by_count":46,"area":null},{"id":"2310.09044","title":"KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","cited_by_count":43,"area":null},{"id":"2403.15734","title":"Space Group Informed Transformer for Crystalline Materials Generation","created":"2024-03-23","cited_by_count":41,"area":null},{"id":"2402.00798","title":"Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents","created":"2024-02-01","cited_by_count":40,"area":"agents"},{"id":"2405.00218","title":"Constrained Decoding for Secure Code Generation","created":"2024-04-30","cited_by_count":37,"area":null},{"id":"2503.02039","title":"Dynamic Search for Inference-Time Alignment in Diffusion Models","created":"2025-03-03","cited_by_count":37,"area":"diffusion"},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2210.02889","title":"A Distributional Lens for Multi-Aspect Controllable Text Generation","created":"2022-10-06","cited_by_count":33,"area":null},{"id":"2301.09919","title":"Opportunities and Challenges in Neural Dialog Tutoring","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33,"area":"lr"},{"id":"2406.13892","title":"Adaptable Logical Control for Large Language Models","created":"2024-06-19","cited_by_count":30,"area":null},{"id":"2208.00638","title":"Composable Text Controls in Latent Space with ODEs","created":"2022-08-01","cited_by_count":28,"area":null},{"id":"2212.08307","title":"Controllable Text Generation via Probability Density Estimation in the Latent Space","created":"2022-12-16","cited_by_count":27,"area":null},{"id":"2401.00690","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","created":"2024-01-01","cited_by_count":27,"area":null},{"id":"2310.11053","title":"Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning","created":"2023-10-17","cited_by_count":26,"area":null},{"id":"2502.00306","title":"Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation","created":"2025-02-01","cited_by_count":26,"area":"rag"},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2305.12018","title":"BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases","created":"2023-05-19","cited_by_count":24,"area":null},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2406.12274","title":"SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models","created":"2024-06-18","cited_by_count":23,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2305.19213","title":"The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code","created":"2023-05-30","cited_by_count":21,"area":"lr"},{"id":"2504.05410","title":"Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","cited_by_count":20,"area":null},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2212.09925","title":"Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2406.00049","title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2410.02163","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2506.05754","title":"Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2504.07081","title":"Self-Steering Language Models","created":"2025-04-09","cited_by_count":13,"area":"lr"},{"id":"2305.12785","title":"MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2504.05804","title":"StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2504.18564","title":"DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization","created":"2025-04-21","cited_by_count":12,"area":"safety"},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2310.18342","title":"MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control","created":"2023-10-22","cited_by_count":11,"area":null},{"id":"2410.13111","title":"Controllable Generation via Locally Constrained Resampling","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2208.00040","title":"Enhanced gradient-based MCMC in discrete spaces","created":"2022-07-29","cited_by_count":10,"area":null},{"id":"2212.09387","title":"An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation","created":"2022-12-19","cited_by_count":10,"area":null},{"id":"2402.19009","title":"Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding","created":"2024-02-29","cited_by_count":10,"area":"diffusion"},{"id":"2310.01991","title":"Fill in the Blank: Exploring and Enhancing LLM Capabilities for Backward Reasoning in Math Word Problems","created":"2023-10-03","cited_by_count":9,"area":"lr"},{"id":"2410.07035","title":"PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness","created":"2024-10-09","cited_by_count":9,"area":"lr"},{"id":"2411.02989","title":"Growing a Tail: Increasing Output Diversity in Large Language Models","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2402.03131","title":"Constrained Decoding for Cross-lingual Label Projection","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8,"area":"alignment"},{"id":"2504.18535","title":"TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation","created":"2025-04-25","cited_by_count":8,"area":"lr"},{"id":"2606.01926","title":"Mitigating Bias in Locally Constrained Decoding via Tractable Proposals","created":"2026-06-01","cited_by_count":8,"area":null},{"id":"2607.26246","title":"Weak-to-Strong On-Policy Distillation","created":"2026-07-28","cited_by_count":8,"area":"distill"},{"id":"2305.19271","title":"Concise Answers to Complex Questions: Summarization of Long-form Answers","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2305.19933","title":"Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind","created":"2023-05-31","cited_by_count":7,"area":null},{"id":"2309.10447","title":"Toward Unified Controllable Text Generation via Regular Expression Instruction","created":"2023-09-19","cited_by_count":7,"area":null},{"id":"2405.01490","title":"Controllable Text Generation in the Instruction-Tuning Era","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2406.08881","title":"No perspective, no perception!! Perspective-aware Healthcare Answer Summarization","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2312.04510","title":"A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2407.21046","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2504.08104","title":"Geneshift: Impact of different scenario shift on Jailbreaking LLM","created":"2025-04-10","cited_by_count":5,"area":"safety"},{"id":"2507.06968","title":"Scaling Towards the Information Boundary of Instruction Sets: The Infinity Instruct Subject Technical Report","created":"2025-07-09","cited_by_count":5,"area":null},{"id":"2603.04948","title":"$\\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space","created":"2026-03-05","cited_by_count":5,"area":"lr"},{"id":"2210.07431","title":"PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2305.19472","title":"PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2306.03061","title":"Structured Voronoi Sampling","created":"2023-06-05","cited_by_count":4,"area":null},{"id":"2311.09741","title":"P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models","created":"2023-11-16","cited_by_count":4,"area":"diffusion"},{"id":"2312.17710","title":"Principled Gradient-based Markov Chain Monte Carlo for Text Generation","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2402.12617","title":"Generative AI Security: Challenges and Countermeasures","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2403.16995","title":"Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows","created":"2024-03-25","cited_by_count":4,"area":"diffusion"}],"next_cursor":"100"}