2 papers
cs.SE2026
On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Quality
Xin Shen, San-Zhuo Xi, Yali Du +1
Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in naturally occurring code, but t…
cs.CR2026
The More It Says, the More You Pay: A Black-Box Audit of Provider-Side Token Inflation in LLM Services
Leilei Chen, Lan Zhang, Chen Tang +5
In pay-per-token LLM services, the more a model says, the more users pay. Dishonest providers can covertly manipulate generation to inflate output tokens while largely preserving t…