Entity · model

SmolVLM-Instruct

modelactiveprovisionalsmolvlm-instruct-9e500752·1 events·first seen 23h ago

Aliases: SmolVLM-Instruct

Co-occurring entities

Qwen2.5-7B-Instruct-1M Small Vision-Language Models Know When They Are Wrong But Cannot Say So

More like this (12)

SmolVLM SmolVLM2 SmolVLM-256M FakeVLM SmolVLA SmolVLM-500M nanoVLM SmolLM SmolLM2 SmolLM3 LLaVA-v1.5-Instruct VLM-IE3D

Recent events (1)

5arXiv · cs.CL·23h ago·source ↗

Small VLMs have usable internal confidence signals that their verbalized outputs fail to express

A new arXiv paper evaluates two small open-weight vision-language models (Qwen2-VL-2B-Instruct and SmolVLM-Instruct) under six realistic image degradations, comparing verbalized confidence against internal token probability as uncertainty signals. Verbalized confidence is found to be nearly constant and near-chance at error detection (AUROC ~0.50), while internal token probability reliably separates correct from incorrect answers (AUROC 0.92–0.99). Both signals fail under severe underexposure, where accuracy collapses but confidence barely moves. The authors conclude that internal probability is the superior deferral signal for constrained deployments, and that small VLMs encode self-knowledge they cannot articulate.

Evaluation and Benchmarking AI Safety Research SmolVLM-Instruct Qwen2.5-7B-Instruct-1M Small Vision-Language Models Know When They Are Wrong But Cannot Say So