arXiv (All)
open access
Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence
Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within individual examples. We study answer-level reliability along five-step, question-conditioned evidence-loss trajectories. Using a frozen Qwen2.5-VL-3B-Instr
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
- MoLE: Mixture of Latent Experts for Complementary Visual Reasoning#1161088
- MoLE: Mixture of Latent Experts for Complementary Visual Reasoning#1157188
- Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting#1123151
- Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs#1061402
- EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology#670694
Record · ID 986957
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