Model Detail
span-02
—span-02 is a multimodal model with 26B parameters released by respanai. The model is registered under the image-text-to-text pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
span-02 ships with 26B parameters. Total weight footprint is approximately 15.8 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
span-02 is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models
arXiv:2608.29974v2 Announce Type: replace-cross Abstract: Detecting hallucinations in Large Vision-Language Models (LVLMs) requires both accurate span localization and well-calibrated confidence scores. Fine-tuned generative VLMs excel at identifying hallucinated text spans but suffer from overconfi
SHAM-Bench: A Span-level Hallucination Benchmark Across Multiple Tasks
arXiv:2610.27370v1 Announce Type: new Abstract: Span-level hallucination detection pinpoints unsupported content in LLM outputs, enabling actionable feedback and targeted mitigation. Existing evaluations for span-level hallucination detection methods are fragmented across tasks, annotation formats,
When Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
arXiv:2610.28393v1 Announce Type: new Abstract: Precisely reproducing a target span verbatim within a long context is a fundamental capability test for LLMs: even when the target string is present in context, models often still drift within the span or fail to stop correctly, revealing limitations i
From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding
arXiv:2603.15270v3 Announce Type: replace-cross Abstract: Medical coding, which assigns standardized ICD codes to clinical documents, is a fundamental yet challenging task in modern healthcare. It requires extensive knowledge of a large code space and the ability to identify and interpret sparse sup
Lowest Span Confidence: Zero-Shot Hallucination Detection from a Single LLM Response
arXiv:2601.19918v2 Announce Type: replace Abstract: Hallucinations in Large Language Models (LLMs), i.e., plausible but non-factual generations, pose a significant challenge to reliable deployment in high-stakes environments. However, many existing hallucination detectors require expensive repeated
External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing
arXiv:2610.02066v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability. While recent internal state probes offer a promising alternative to slow external retrieval systems, t
