Co-design of LLM-based preference agents: participation may drive overtrust

arXiv 2607.21757•d324b8ae2cbf3d05bc6c410251094389de6aea106671652af569aec52699b04d
accessibilityagentic-systemsai-governanceartificial-intelligencecopyright-compliancedeployment-configurationeu-ai-acthuman-ai-interactionlarge-language-modelsllm-safetymodel-reliabilityopaque-updatesovertrustprompt-sensitivitypsychological-dependencyregulatory-compliancerequirements-engineeringtime-pressure

Paper metadata

arXiv ID
2607.21757
Version
Not specified by this published record
Category
Computer Science — Computers and Society (cs.CY)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_cy
Record identifier
d324b8ae2cbf3d05bc6c410251094389de6aea106671652af569aec52699b04d
Enrichment time
2026-07-27T07:23:45Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.