Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.
Lost in the middle: How language models use long contexts
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
citing papers explorer
-
CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.