Cover Image

From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Yu, Wu, Shuo, Tao, Ye, Li, Yansong, Sarwate, Anand D.
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral
by: Farinhas, António, et al.
Published: (2025)

LLM-Oriented Token-Adaptive Knowledge Distillation
by: Xie, Xurong, et al.
Published: (2025)

Learning to Help in Multi-Class Settings
by: Wu, Yu, et al.
Published: (2025)

RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
by: Liu, Xiao, et al.
Published: (2025)

Multimodal Commonsense Knowledge Distillation for Visual Question Answering
by: Yang, Shuo, et al.
Published: (2024)

LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models
by: Yang, Runming, et al.
Published: (2024)

Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models
by: Wu, Taiqiang, et al.
Published: (2024)

HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification
by: Paudel, Bibek, et al.
Published: (2025)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
by: Xiao, Yilin, et al.
Published: (2025)

IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
by: Shi, Dan, et al.
Published: (2024)

Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities
by: Padmanabhan, Shankar, et al.
Published: (2026)

Self-Knowledge Distillation for Learning Ambiguity
by: Park, Hancheol, et al.
Published: (2024)

Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments
by: Latif, Ehsan, et al.
Published: (2023)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
by: Ning, Yansong, et al.
Published: (2025)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
by: Wang, Jianing, et al.
Published: (2023)

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
by: Jiang, Bo
Published: (2026)

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection
by: Huang, Hsiu-Yuan, et al.
Published: (2024)

Federated In-Context LLM Agent Learning
by: Wu, Panlong, et al.
Published: (2024)

Distilling Event Sequence Knowledge From Large Language Models
by: Wadhwa, Somin, et al.
Published: (2024)

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
by: Dai, Chengwei, et al.
Published: (2024)

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

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
by: Duan, Shaohua, et al.
Published: (2025)

Black-Box On-Policy Distillation of Large Language Models
by: Ye, Tianzhu, et al.
Published: (2025)

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades
by: Chang, Raeyoung, et al.
Published: (2026)

PMMT: Preference Alignment in Multilingual Machine Translation via LLM Distillation
by: Sun, Shuqiao, et al.
Published: (2024)

MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning
by: Li, Yichuan, et al.
Published: (2024)

Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering
by: Tao, Mingxu, et al.
Published: (2024)

Distilling Closed-Source LLM's Knowledge for Locally Stable and Economic Biomedical Entity Linking
by: Ai, Yihao, et al.
Published: (2025)

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
by: Dai, Sunhao, et al.
Published: (2025)

AutoContext: Instance-Level Context Learning for LLM Agents
by: Cai, Kuntai, et al.
Published: (2025)

From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction
by: Li, Ang, et al.
Published: (2024)

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
by: Li, Pingzhi, et al.
Published: (2025)

Reinforcement Learning for Conversational Question Answering over Knowledge Graph
by: Wu, Mi
Published: (2024)

Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning
by: Wu, Yang, et al.
Published: (2024)

Demonstration Selection for In-Context Learning via Reinforcement Learning
by: Wang, Xubin, et al.
Published: (2024)

From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering
by: Li, Lei, et al.
Published: (2025)

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
by: Wu, Yuchen, et al.
Published: (2025)

Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict
by: Sun, Kaiser, et al.
Published: (2025)

M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization
by: Bai, Bizhe, et al.
Published: (2025)

KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
by: Wei, Yanbin, et al.
Published: (2024)