Retrospective Distillation Attribution via Normalized Response Similarity
cs.AI, cs.CL, cs.CR, cs.LG, stat.ML
Submitted: 2026-09-26
Updated: 2026-09-26
Comments: Preprint
Code: https://github.com/Qihoo360/Light-R1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Language Models are Few-Shot Learners
- AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
- Training Verifiers to Solve Math Word Problems
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
- The Llama 3 Herd of Models
- Skywork Open Reasoner 1 Technical Report
- Mistral 7B
- DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
- DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
- s1: Simple test-time scaling
- Olmo 3
- GPT-4o System Card
- OpenAI o1 System Card
- gpt-oss-120b & gpt-oss-20b Model Card
- Reference-Based Distillation Detection in LLMs
- TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems