Metraipolis › archive › dc_f2c8f3b79574

Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization — arXiv:2609.14839

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14839
License (as archived)
CC0-1.0
Archived
2026-10-15T22:53:22.754Z
SHA-256 of the archived text
3c16fbe46e51ad2bed86352f1b31703e0471cdcfb979d33cc209a797cde6af88
Stable URL of this page
https://metraipolis.com/documento/dc_f2c8f3b79574

How to cite

Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization — arXiv:2609.14839 — arXiv (en), https://arxiv.org/abs/2609.14839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f2c8f3b79574 (Metraipolis archive dc_f2c8f3b79574, sha256 3c16fbe46e51ad2bed86352f1b31703e0471cdcfb979d33cc209a797cde6af88)
BibTeX
@misc{dcf2c8f3b79574,
  title = {Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization — arXiv:2609.14839},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14839},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f2c8f3b79574; sha256 3c16fbe46e51ad2bed86352f1b31703e0471cdcfb979d33cc209a797cde6af88},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Hallucination: an LLM's tendency to issue non-functional mutations with unsubstantiated performance claims on already-optimized code. This is driven by the Evaluation Trap, wherein binary benchmarks incentivize unnecessary modifications over safely abstaining. We present a validation framework using classification penalty methods, evaluated across 180 optimization runs on nine models (GPT, Claude, Gemini) using EffiBench. Under standard prompts, models exhibit a 100% over-edit rate on optimal code. Our guardrail raises correct abstention from 0% to to 44.4%, preserving a 100% edit rate on sub-optimal code with zero false abstentions. Calibration is uneven: GPT-5.4 Mini approaches near-perfect abstention, and simple code is recognized more reliably than complex code. Our framework offers a training-free mechanism to mitigate LLM overconfidence before deployment in production.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14839 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.738Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).