Linear probes on frozen LLM hidden states recover an approximate remaining-output-length signal that is decodable at prompt-end, transfers across datasets, and shifts upward at retraction tokens.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
First detailed breakdown of vLLM startup into six CPU-bound steps with scaling trends yields a lightweight analytical model that predicts latency for given hardware configurations.
A structured survey of LLM mathematical reasoning that unifies dataset taxonomies, reviews architectures and training strategies, and highlights the gap between answer accuracy and process-level verification.
citing papers explorer
-
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Linear probes on frozen LLM hidden states recover an approximate remaining-output-length signal that is decodable at prompt-end, transfers across datasets, and shifts upward at retraction tokens.
-
Breaking the Ice: Analyzing Cold Start Latency in vLLM
First detailed breakdown of vLLM startup into six CPU-bound steps with scaling trends yields a lightweight analytical model that predicts latency for given hardware configurations.
-
Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
A structured survey of LLM mathematical reasoning that unifies dataset taxonomies, reviews architectures and training strategies, and highlights the gap between answer accuracy and process-level verification.