arXiv (All)
open access
Single-Query Black-Box Calibration Auditing via Logit Bias
Evaluating the calibration of Large Language Models (LLMs) is critical for their safe deployment as zero-shot classifiers. Yet, commercial API providers increasingly hide the continuous output probabilities required by standard calibration metrics. To bypass this opacity, we demonstrate that any LLM
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration#1129977
- Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models#160720
- Dataset Watermarking with Provable Black-Box Detection#1130546
- The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference#1084260
- Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning#799861
Record · ID 972074
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive