{"total":87,"rows":[{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2211.00053","title":"Generating Sequences by Learning to Self-Correct","created":"2022-10-31","cited_by_count":277,"area":null},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97,"area":null},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2310.04742","title":"Parameter Efficient Multi-task Model Fusion with Partial Linearization","created":"2023-10-07","cited_by_count":65,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2212.10938","title":"Critic-Guided Decoding for Controlled Text Generation","created":"2022-12-21","cited_by_count":45,"area":null},{"id":"2210.03078","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","created":"2022-10-06","cited_by_count":43,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41,"area":null},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39,"area":null},{"id":"2401.06081","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","created":"2024-01-11","cited_by_count":39,"area":null},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37,"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":"2303.17574","title":"Elastic Weight Removal for Faithful and Abstractive Dialogue Generation","created":"2023-03-30","cited_by_count":29,"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":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","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":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2302.03686","title":"Long Horizon Temperature Scaling","created":"2023-02-07","cited_by_count":18,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2403.11558","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2311.07167","title":"STEER: Unified Style Transfer with Expert Reinforcement","created":"2023-11-13","cited_by_count":14,"area":null},{"id":"2407.07089","title":"Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic","created":"2024-07-09","cited_by_count":14,"area":null},{"id":"2402.12621","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2403.08043","title":"Authorship Style Transfer with Policy Optimization","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2306.04707","title":"Improving Open Language Models by Learning from Organic Interactions","created":"2023-06-07","cited_by_count":10,"area":null},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10,"area":null},{"id":"2211.16773","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning","created":"2022-11-30","cited_by_count":9,"area":null},{"id":"2305.13829","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2406.12221","title":"On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation","created":"2024-06-18","cited_by_count":9,"area":null},{"id":"2305.19339","title":"Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2310.18679","title":"N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics","created":"2023-10-28","cited_by_count":8,"area":null},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2303.04562","title":"Extrapolative Controlled Sequence Generation via Iterative Refinement","created":"2023-03-08","cited_by_count":7,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2410.06716","title":"Guaranteed Generation from Large Language Models","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2501.06911","title":"Risk-Averse Finetuning of Large Language Models","created":"2025-01-12","cited_by_count":7,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2307.12425","title":"On the Effectiveness of Offline RL for Dialogue Response Generation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2505.19533","title":"ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2310.18804","title":"Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2507.01409","title":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2312.06149","title":"Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2406.16229","title":"Multi-Objective Linguistic Control of Large Language Models","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2505.20966","title":"Personalized Query Auto-Completion for Long and Short-Term Interests with Adaptive Detoxification Generation","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2309.16231","title":"Controllable Text Generation with Residual Memory Transformer","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2406.16672","title":"CAVE: Controllable Authorship Verification Explanations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2311.07430","title":"Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2503.11182","title":"Palette of Language Models: A Solver for Controlled Text Generation","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2504.21043","title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2505.03052","title":"Teaching Models to Understand (but not Generate) High-risk Data","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2511.06818","title":"Learning to Focus: Focal Attention for Selective and Scalable Transformers","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2310.01248","title":"Improving Emotional Expression and Cohesion in Image-Based Playlist Description and Music Topics: A Continuous Parameterization Approach","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2310.09017","title":"Dont Add, dont Miss: Effective Content Preserving Generation from Pre-Selected Text Spans","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2311.08300","title":"Workflow-Guided Response Generation for Task-Oriented Dialogue","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2403.15351","title":"Multi-Review Fusion-in-Context","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2405.14596","title":"Linear Mode Connectivity in Differentiable Tree Ensembles","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2406.13660","title":"Towards Minimal Targeted Updates of Language Models with Targeted Negative Training","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2407.13048","title":"Establishing Knowledge Preference in Language Models","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2506.01266","title":"Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.05940","title":"Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2510.14845","title":"Backdoor Unlearning by Linear Task Decomposition","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2311.09732","title":"Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2510.21184","title":"Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2605.14004","title":"Conditional Attribute Estimation with Autoregressive Sequence Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.21090","title":"Training Large Language Models for Self-Explanation Faithfulness","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.33638","title":"Quantifying Behavioral Tails in Black-Box Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.03240","title":"Collective Bias Mitigation via Model Routing and Collaboration","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}