KETCHUP: K-Step Return Estimation for Sequential Knowledge Distillation

arXiv:2504.19024 · cs.CL · Submitted 2025-04-26 · Read on arXiv

cs.CL

Submitted: 2025-04-26

Updated: 2026-10-19

Comments: Accepted to EACL 2026

Journal ref: Findings of the Association for Computational Linguistics: EACL 2026

DOI: 10.18653/v1/2026.findings-eacl.39

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 2× in this paper · explained in 2 episodes
• Knowledge Distillation — 2× in this paper · explained in 14 episodes
• Knowledge Distillation (KD) — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering