Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
TriQua: Reconciling Granularity and Context in Factuality Evaluation
Jin Liu, Steffen Thoma, Achim Rettinger
The "decompose-then-verify" paradigm for LLM factuality evaluation faces a fundamental trade-off: atomic facts, i.e., one sentence conveying one unit of information, often omit ess…
cs.AI2025
POV Learning: Individual Alignment of Multimodal Models using Human Perception
Simon Werner, Katharina Christ, Laura Bernardy +2
Aligning machine learning systems with human expectations is mostly attempted by training with manually vetted human behavioral samples, typically explicit feedback. This is done o…