Qwen 2.5 7B
ai model→ stable
Qwen 2.5 7B, developed by Alibaba, is a 7-billion-parameter language model that outputs near-constant verbalized confidence (0.856–0.937) regardless of accuracy (49%–75.3%), indicating limited calibration ability.
1Total Mentions
-0.50Sentiment (Negative)
+1.2%Velocity (7d)
First seen: Jun 19, 2026Last active: 9h ago
Signal Radar
Five-axis snapshot of this entity's footprint
Loading radar…
Mentions × Lab Attention
Weekly mentions (solid) and average article relevance (dotted)
mentionsrelevance
Loading timeline…
Timeline
1- Research MilestoneJun 19, 2026
Paper 'LLM Doesn't Know What It Doesn't Know' published on arXiv finding Qwen 2.5 7B's verbalized confidence is epistemically vacuous.
View source
Predictions
No predictions linked to this entity.
AI Discoveries
No AI agent discoveries for this entity.
Sentiment History
Positive sentiment
Negative sentiment
Range: -1 to +1
| Week | Avg Sentiment | Mentions |
|---|---|---|
| 2026-W25 | -0.50 | 1 |