Copertina

Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Wei-Rui, Kothapalli, Vignesh, Fatahibaarzi, Ata, Sang, Hejian, Tang, Shao, Song, Qingquan, Wang, Zhipeng, Abdul-Mageed, Muhammad
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
di: Kothapalli, Vignesh, et al.
Pubblicazione: (2025)

To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation
di: Waheed, Abdul, et al.
Pubblicazione: (2024)

uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes
di: Waheed, Abdul, et al.
Pubblicazione: (2024)

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
di: Wu, Minghao, et al.
Pubblicazione: (2023)

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
di: Sang, Hejian, et al.
Pubblicazione: (2026)

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
di: Chen, Xiwen, et al.
Pubblicazione: (2026)

PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

Distilling Text Style Transfer With Self-Explanation From LLMs
di: Zhang, Chiyu, et al.
Pubblicazione: (2024)

Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems
di: Behdin, Kayhan, et al.
Pubblicazione: (2025)

Interplay of Machine Translation, Diacritics, and Diacritization
di: Chen, Wei-Rui, et al.
Pubblicazione: (2024)

Liger Kernel: Efficient Triton Kernels for LLM Training
di: Hsu, Pin-Lun, et al.
Pubblicazione: (2024)

AfroScope: A Framework for Studying the Linguistic Landscape of Africa
di: Kwon, Sang Yun, et al.
Pubblicazione: (2026)

TIP: Token Importance in On-Policy Distillation
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
di: Waheed, Abdul, et al.
Pubblicazione: (2025)

Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
di: Ko, Jongwoo, et al.
Pubblicazione: (2026)

Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs
di: Mekki, Abdellah El, et al.
Pubblicazione: (2024)

CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations
di: Kothapalli, Vignesh, et al.
Pubblicazione: (2025)

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
di: He, Junlin, et al.
Pubblicazione: (2026)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
di: Yan, Shaotian, et al.
Pubblicazione: (2026)

On Barriers to Archival Audio Processing
di: Sullivan, Peter, et al.
Pubblicazione: (2025)

LLM-Guided Knowledge Distillation for Temporal Knowledge Graph Reasoning
di: Xing, Wang, et al.
Pubblicazione: (2026)

Fumbling in Babel: An Investigation into ChatGPT's Language Identification Ability
di: Chen, Wei-Rui, et al.
Pubblicazione: (2023)

Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
di: Zhu, Siyu, et al.
Pubblicazione: (2025)

Knowledge Distillation for Temporal Knowledge Graph Reasoning with Large Language Models
di: Xing, Wang, et al.
Pubblicazione: (2026)

Towards Zero-Shot Text-To-Speech for Arabic Dialects
di: Doan, Khai Duy, et al.
Pubblicazione: (2024)

RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
di: Xu, Shicheng, et al.
Pubblicazione: (2025)

Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic
di: Alwajih, Fakhraddin, et al.
Pubblicazione: (2024)

Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
di: Li, Pingzhi, et al.
Pubblicazione: (2025)

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
di: Wu, Tong, et al.
Pubblicazione: (2025)

Toucan: Many-to-Many Translation for 150 African Language Pairs
di: Elmadany, AbdelRahim, et al.
Pubblicazione: (2024)

Zero-Shot Context-Aware ASR for Diverse Arabic Varieties
di: Talafha, Bashar, et al.
Pubblicazione: (2025)

Cheetah: Natural Language Generation for 517 African Languages
di: Adebara, Ife, et al.
Pubblicazione: (2024)

Effective Distillation of Table-based Reasoning Ability from LLMs
di: Yang, Bohao, et al.
Pubblicazione: (2023)

Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
di: Zhang, Lechen, et al.
Pubblicazione: (2026)

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
di: Zhou, Yuhang, et al.
Pubblicazione: (2024)

Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
di: Xu, Yuanda, et al.
Pubblicazione: (2026)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
di: Zhao, Siyan, et al.
Pubblicazione: (2026)

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
di: Liu, Zhenghao, et al.
Pubblicazione: (2026)

Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation
di: Yu, Fengming, et al.
Pubblicazione: (2025)

Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer
di: Zhang, Xiang, et al.
Pubblicazione: (2024)