Any deterministic prompt filter for code LLMs has a provable mutual-information lower bound of at least 0.84 nats on HumanEval and 1.20 nats on MBPP under pass-only acceptance, with no tested filter achieving zero proxy-axis leakage.
arXiv preprint arXiv:2511.16209 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An LLM semantic-matching framework for journal recommendation reports 40.23% Top-3 accuracy on 23,609 statistics articles from 49 journals without task-specific training.
citing papers explorer
-
The Security Budget of Code-LLM Prompt Hardening: Provable Limits Under Pass-Only Acceptance
Any deterministic prompt filter for code LLMs has a provable mutual-information lower bound of at least 0.84 nats on HumanEval and 1.20 nats on MBPP under pass-only acceptance, with no tested filter achieving zero proxy-axis leakage.
-
An LLM-Powered Semantic Alignment Framework for Journal Recommendation
An LLM semantic-matching framework for journal recommendation reports 40.23% Top-3 accuracy on 23,609 statistics articles from 49 journals without task-specific training.