arXiv (All)
open access
A$^2$Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
Visual Question Answering (VQA) with Multimodal Large Language Models (MLLMs) requires not only producing safe and effective responses, but also grounding safety decisions in the multimodal evidence that determines risk. Recent safety-alignment methods improve refusal behavior and contextual risk aw
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
- Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment#985564
- From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models#1116984
- Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs#1061402
- Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation#1109846
- Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations#1156399
Record · ID 1050284
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