Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning
Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers. Existing retrieval-augmented methods score image-text alignment once, at retrieval, then commit the captioner's autoregressive beam under language-model probability alone, leaving the decoder without further visual grounding feedback. Progress has stalled, with no method improving on the strict-regime best sin
Record details
Published: 31 July 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 3 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Fragility of Value under Imperfect Alignment
arXiv · 30 July 2026
ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
arXiv · 31 July 2026
Inference-Time Policy Alignment for Fair Reinforcement Learning
arXiv fairness query · 31 July 2026
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
HuggingFace Daily Papers · 31 July 2026
The Agency Gap in AI-Supported Writing: How Reactive and Proactive Agent Designs Shape Multimodal Reasoning
arXiv cs.CY · 30 July 2026
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
arXiv cs.CY · 30 July 2026
How to cite this record
ethics.ai (31 July 2026), “Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning,” evidence record 15683, https://ethics.ai/record/15683 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.