ResearchNov 16, 2026 · 12:001 source

Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs

From arxiv.org

AI;DR

A one-GPU audit examined four hallucination detectors on small, quantized, on-device LLMs including Phi-3-mini and Llama-3.2-3B-Instruct. Cross-model ranking transfer was poor, with Spearman rho at -0.80 and Kendall tau-b at -0.667. The cheap lexical baseline was statistically indistinguishable from the sampling-based consistency detectors on both models.

Read the sourceSign in to suggest

Sources

#llmMarkdown

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today