{"total":93,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157,"area":null},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2303.14742","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","created":"2023-03-26","cited_by_count":86,"area":null},{"id":"2405.20541","title":"Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models","created":"2024-05-30","cited_by_count":84,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2311.09410","title":"When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour","created":"2023-11-15","cited_by_count":62,"area":null},{"id":"2305.14908","title":"PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions","created":"2023-05-24","cited_by_count":53,"area":null},{"id":"2309.11696","title":"LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination","created":"2023-09-21","cited_by_count":46,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2510.04340","title":"Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time","created":"2025-10-05","cited_by_count":43,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","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":"2404.03565","title":"Personalized LLM Response Generation with Parameterized Memory Injection","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2409.14703","title":"MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification","created":"2024-09-23","cited_by_count":30,"area":null},{"id":"2405.02501","title":"PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning","created":"2024-05-03","cited_by_count":29,"area":null},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25,"area":null},{"id":"2305.10314","title":"LeTI: Learning to Generate from Textual Interactions","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2305.18449","title":"Taming AI Bots: Controllability of Neural States in Large Language Models","created":"2023-05-29","cited_by_count":22,"area":null},{"id":"2311.08576","title":"Towards Evaluating AI Systems for Moral Status Using Self-Reports","created":"2023-11-14","cited_by_count":22,"area":null},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22,"area":null},{"id":"2304.07854","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","created":"2023-04-16","cited_by_count":20,"area":null},{"id":"2404.07242","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","created":"2024-04-09","cited_by_count":20,"area":null},{"id":"2605.02087","title":"Model Spec Midtraining: Improving How Alignment Training Generalizes","created":"2026-05-03","cited_by_count":20,"area":null},{"id":"2304.08109","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2406.01026","title":"Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2502.03382","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","created":"2025-02-05","cited_by_count":15,"area":null},{"id":"2310.02469","title":"PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2503.09202","title":"Token Weighting for Long-Range Language Modeling","created":"2025-03-12","cited_by_count":14,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2311.14711","title":"Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework","created":"2023-11-15","cited_by_count":11,"area":null},{"id":"2411.02688","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2511.04962","title":"Too Good to be Bad: On the Failure of LLMs to Role-Play Villains","created":"2025-11-07","cited_by_count":11,"area":null},{"id":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2304.11220","title":"Learn What NOT to Learn: Towards Generative Safety in Chatbots","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2405.05418","title":"Mitigating Exaggerated Safety in Large Language Models","created":"2024-05-08","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2410.04838","title":"Rationale-Aware Answer Verification by Pairwise Self-Evaluation","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2605.12798","title":"Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer","created":"2026-05-12","cited_by_count":8,"area":null},{"id":"2310.02457","title":"The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising \"Alignment\" in Large Language Models","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2410.13901","title":"SoK: Prompt Hacking of Large Language Models","created":"2024-10-16","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":"2405.19265","title":"AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data","created":"2024-05-29","cited_by_count":6,"area":null},{"id":"2308.07429","title":"Semantic Similarity Loss for Neural Source Code Summarization","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2308.09720","title":"On the Unexpected Abilities of Large Language Models","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2309.14805","title":"Fine-tuning and aligning question answering models for complex information extraction tasks","created":"2023-09-26","cited_by_count":5,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2405.16579","title":"Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse Granularity","created":"2024-05-26","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":"2306.11393","title":"The Cultivated Practices of Text-to-Image Generation","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2410.14147","title":"Leveraging Large Language Models for Enhancing Public Transit Services","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2504.17562","title":"When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2306.07567","title":"Large Language Models Sometimes Generate Purely Negatively-Reinforced Text","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2408.15658","title":"An Empirical Study on Self-correcting Large Language Models for Data Science Code Generation","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2410.17271","title":"Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2501.01741","title":"How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models","created":"2025-01-03","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":"2505.17131","title":"Relative Bias: A Comparative Framework for Quantifying Bias in LLMs","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2310.16062","title":"Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning","created":"2023-10-24","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":"2502.07072","title":"IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models","created":"2025-02-10","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":"2510.13393","title":"Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.27629","title":"Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.09287","title":"From Model Training to Model Raising","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2309.00751","title":"Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence","created":"2023-09-01","cited_by_count":0,"area":null},{"id":"2309.06415","title":"Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models","created":"2023-09-08","cited_by_count":0,"area":null},{"id":"2405.06915","title":"Automating Creativity","created":"2024-05-11","cited_by_count":0,"area":null},{"id":"2412.10257","title":"Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2501.07324","title":"Foundation Models at Work: Fine-Tuning for Fairness in Algorithmic Hiring","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2510.20428","title":"An Empirical Study of Sample Selection Strategies for Large Language Model Repair","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.15236","title":"MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2609.33405","title":"Decoupling Token Roles in Autoregressive Pretraining","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.00309","title":"Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}