Copertina

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Yinghui, Kaur, Simran, Bhaskar, Adithya, Yang, Yongjin, Liu, Jiarui, Ri, Narutatsu, Fowl, Liam, Panigrahi, Abhishek, Chen, Danqi, Arora, Sanjeev
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models
di: He, Yinghui, et al.
Pubblicazione: (2025)

Skill-Targeted Adaptive Training
di: He, Yinghui, et al.
Pubblicazione: (2025)

Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
di: Razin, Noam, et al.
Pubblicazione: (2024)

How Does RL Post-training Induce Skill Composition? A Case Study on Countdown
di: Park, Simon, et al.
Pubblicazione: (2025)

On the Power of Context-Enhanced Learning in LLMs
di: Zhu, Xingyu, et al.
Pubblicazione: (2025)

The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
di: Bhaskar, Adithya, et al.
Pubblicazione: (2024)

Language Models that Think, Chat Better
di: Bhaskar, Adithya, et al.
Pubblicazione: (2025)

MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
di: Liu, Jiarui, et al.
Pubblicazione: (2026)

The unregulated plant‐based ‘milk’ industry: A threat to nutrition, health and safety?
di: Simran Kaur Arora
Pubblicazione: (2024)

Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
di: Dang, Xingyu, et al.
Pubblicazione: (2026)

Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
di: Kaur, Simran, et al.
Pubblicazione: (2024)

Trainable Transformer in Transformer
di: Panigrahi, Abhishek, et al.
Pubblicazione: (2023)

On the SDEs and Scaling Rules for Adaptive Gradient Algorithms
di: Malladi, Sadhika, et al.
Pubblicazione: (2022)

Representing Rule-based Chatbots with Transformers
di: Friedman, Dan, et al.
Pubblicazione: (2024)

Reranking-based Generation for Unbiased Perspective Summarization
di: Ri, Narutatsu, et al.
Pubblicazione: (2025)

Finding Transformer Circuits with Edge Pruning
di: Bhaskar, Adithya, et al.
Pubblicazione: (2024)

Improving Language Understanding from Screenshots
di: Gao, Tianyu, et al.
Pubblicazione: (2024)

Extracting Rule-based Descriptions of Attention Features in Transformers
di: Friedman, Dan, et al.
Pubblicazione: (2025)

Why is Your Language Model a Poor Implicit Reward Model?
di: Razin, Noam, et al.
Pubblicazione: (2025)

Can Models Learn Skill Composition from Examples?
di: Zhao, Haoyu, et al.
Pubblicazione: (2024)

3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering
di: Krishnan, Meenakshi, et al.
Pubblicazione: (2025)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
di: Chan, Yik Siu, et al.
Pubblicazione: (2025)

Continual Memorization of Factoids in Language Models
di: Chen, Howard, et al.
Pubblicazione: (2024)

Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
di: Bhaskar, Adithya, et al.
Pubblicazione: (2025)

Zero-shot Active Learning Using Self Supervised Learning
di: Sinha, Abhishek, et al.
Pubblicazione: (2024)

CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards
di: Lin, Zhiming, et al.
Pubblicazione: (2025)

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning
di: Lazić, Nevena, et al.
Pubblicazione: (2026)

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
di: Park, Simon, et al.
Pubblicazione: (2025)

Late Time Acceleration with Observational Constraints in Modified Theories of Gravity
di: Arora, Simran
Pubblicazione: (2023)

Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
di: Wang, Longwen, et al.
Pubblicazione: (2026)

Embedding Generalized CP Symmetry in One Zero Texture Neutrino Mass Models
di: Priya, et al.
Pubblicazione: (2025)

GenVC: Self-Supervised Zero-Shot Voice Conversion
di: Cai, Zexin, et al.
Pubblicazione: (2025)

LESS: Selecting Influential Data for Targeted Instruction Tuning
di: Xia, Mengzhou, et al.
Pubblicazione: (2024)

On the Impossibility of Retrain Equivalence in Machine Unlearning
di: Yu, Jiatong, et al.
Pubblicazione: (2025)

Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
di: Didolkar, Aniket, et al.
Pubblicazione: (2025)

Occlusion-Aware Self-Supervised Monocular Depth Estimation for Weak-Texture Endoscopic Images
di: Huang, Zebo, et al.
Pubblicazione: (2025)

Tailoring Self-Rationalizers with Multi-Reward Distillation
di: Ramnath, Sahana, et al.
Pubblicazione: (2023)

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
di: Tomihari, Akiyoshi, et al.
Pubblicazione: (2026)

p-(001)NiO/n-(0001)ZnO heterostructures grown by pulsed laser deposition technique
di: Sahu, Bhabani Prasad, et al.
Pubblicazione: (2024)

Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
di: Lowe, Scott C., et al.
Pubblicazione: (2026)