{"total":138,"rows":[{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493,"area":"safety"},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390,"area":null},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356,"area":null},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308,"area":"lr"},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267,"area":null},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256,"area":"rag"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2307.06945","title":"In-context Autoencoder for Context Compression in a Large Language Model","created":"2023-07-13","cited_by_count":199,"area":"inference"},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2212.00193","title":"Distilling Reasoning Capabilities into Smaller Language Models","created":"2022-12-01","cited_by_count":158,"area":"lr"},{"id":"2307.16888","title":"Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection","created":"2023-07-31","cited_by_count":157,"area":"safety"},{"id":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108,"area":"lr"},{"id":"2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","created":"2026-03-25","cited_by_count":103,"area":"lr"},{"id":"2602.04942","title":"Privileged Information Distillation for Language Models","created":"2026-02-04","cited_by_count":90,"area":"distill"},{"id":"2604.10674","title":"Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents","created":"2026-04-12","cited_by_count":90,"area":"agents"},{"id":"2506.06266","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","created":"2025-06-06","cited_by_count":86,"area":"inference"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2604.12002","title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","created":"2026-04-13","cited_by_count":68,"area":"distill"},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67,"area":"agents"},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50,"area":"mllm"},{"id":"2310.13798","title":"Specific versus General Principles for Constitutional AI","created":"2023-10-20","cited_by_count":47,"area":"alignment"},{"id":"2404.01077","title":"Efficient Prompting Methods for Large Language Models: A Survey","created":"2024-04-01","cited_by_count":47,"area":null},{"id":"2307.12950","title":"RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment","created":"2023-07-24","cited_by_count":43,"area":"alignment"},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2502.03492","title":"Teaching Language Models to Critique via Reinforcement Learning","created":"2025-02-05","cited_by_count":42,"area":"lr"},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2503.07826","title":"Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation","created":"2025-03-10","cited_by_count":37,"area":"agents"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2406.11194","title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","created":"2024-06-17","cited_by_count":34,"area":null},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"id":"2506.14728","title":"AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes","created":"2025-06-17","cited_by_count":30,"area":"agents"},{"id":"2306.09306","title":"Propagating Knowledge Updates to LMs Through Distillation","created":"2023-06-15","cited_by_count":28,"area":null},{"id":"2603.12273","title":"Aligning Language Models from User Interactions","created":"2026-02-18","cited_by_count":28,"area":"alignment"},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24,"area":"distill"},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2402.10893","title":"RLVF: Learning from Verbal Feedback without Overgeneralization","created":"2024-02-16","cited_by_count":19,"area":"alignment"},{"id":"2602.23008","title":"Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization","created":"2026-02-26","cited_by_count":19,"area":"agents"},{"id":"2410.23214","title":"Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval","created":"2024-10-30","cited_by_count":17,"area":null},{"id":"2403.06914","title":"MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2210.17525","title":"Query Refinement Prompts for Closed-Book Long-Form Question Answering","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2608.09228","title":"Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":12,"area":"distill"},{"id":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2510.13842","title":"ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking","created":"2025-10-11","cited_by_count":10,"area":"rag"},{"id":"2605.17497","title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","created":"2026-05-17","cited_by_count":10,"area":"lr"},{"id":"2605.22263","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2603.15500","title":"Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty","created":"2026-03-16","cited_by_count":9,"area":"lr"},{"id":"2604.16830","title":"The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation","created":"2026-04-18","cited_by_count":9,"area":"distill"},{"id":"2605.11613","title":"From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation","created":"2026-05-12","cited_by_count":9,"area":"distill"},{"id":"2310.02174","title":"Ask Again, Then Fail: Large Language Models' Vacillations in Judgment","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2502.01562","title":"Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization","created":"2025-02-03","cited_by_count":8,"area":"agents"},{"id":"2506.14111","title":"Essential-Web v1.0: 24T tokens of organized web data","created":"2025-06-17","cited_by_count":8,"area":null},{"id":"2604.26573","title":"PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners","created":"2026-04-29","cited_by_count":8,"area":"lr"},{"id":"2406.02847","title":"Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2607.01763","title":"Denser $\\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training","created":"2026-07-02","cited_by_count":7,"area":"distill"},{"id":"2412.07393","title":"CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2607.13643","title":"Consensus as Privileged Context for Label-Free Self-Distillation","created":"2026-07-15","cited_by_count":5,"area":"lr"},{"id":"2409.01930","title":"Efficient LLM Context Distillation","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2412.13243","title":"In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning","created":"2024-12-17","cited_by_count":4,"area":"distill"},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4,"area":"lr"},{"id":"2606.04703","title":"Rethinking Continual Experience Internalization for Self-Evolving LLM Agents","created":"2026-06-03","cited_by_count":4,"area":"lr"},{"id":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"id":"2602.16093","title":"Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2604.20733","title":"Learning from the Near Future: Temporal Self-Distillation for RLVR","created":"2026-04-22","cited_by_count":3,"area":"distill"},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2606.02437","title":"On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2607.21051","title":"Sample-Efficient Learning from Agent Experience","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2607.22629","title":"Masked Distillation: Internalizing the Chain-of-Thought in Language Models","created":"2026-06-18","cited_by_count":3,"area":"lr"},{"id":"2508.17032","title":"Learned Structure in Cartridges: Keys as Shareable Routers in Self-Studied Representations","created":"2025-08-23","cited_by_count":2,"area":"inference"},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2606.12400","title":"Doc-to-Atom: Learning to Compile and Compose Memory Atoms","created":"2026-06-10","cited_by_count":2,"area":"lr"},{"id":"2608.01672","title":"Learning What to Remember: Test-Time Training via Context Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2609.25623","title":"What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation","created":"2026-09-22","cited_by_count":2,"area":"distill"},{"id":"2212.09721","title":"KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales","created":"2022-12-19","cited_by_count":1,"area":"lr"},{"id":"2505.22907","title":"Conversational Alignment with Artificial Intelligence in Context","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.22621","title":"IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2512.17053","title":"Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL","created":"2025-12-18","cited_by_count":1,"area":"lr"},{"id":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.20258","title":"It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs","created":"2026-05-18","cited_by_count":1,"area":"distill"},{"id":"2606.16149","title":"Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.01690","title":"Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.28022","title":"Flux-OPD: On-Policy Distillation with Evolving Contexts","created":"2026-07-30","cited_by_count":1,"area":"distill"},{"id":"2609.23466","title":"RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents","created":"2026-09-20","cited_by_count":1,"area":"agents"},{"id":"2609.36642","title":"PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.03039","title":"HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning","created":"2026-10-02","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}