LLM Digest

Story

arxiv_cs_lg · Oct 27, 2026 · paper

Source brief

When Visual Evidence Is Insufficient: How Instructions, Post-Training, and Internal Activations Shape Refusal in Multimodal Language Models

arxiv.orgOct 27, 2026
original source linked

In brief

For reliable deployment, multimodal large language models (MLLMs) should recognize when an image provides insufficient evidence to answer a question and withhold unsupported answers. Yet refusal alone is not necessari...

Read the original at arxiv.org →Open in live feed Read that day’s brief

When Visual Evidence Is Insufficient: How Instructions, Post-Training, and Internal Activations Shape Refusal in Multimodal Language Models

Earlier in this thread 4 items

Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation

A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System