Dense retrievers favor passages naming high-scoring answer objects
Across eight models, higher token-prediction scores predict higher retrieval ranks even when the relation is wrong.
34
AI model
Contriever
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenOct 17, 2026
- Last mentioned3d ago
Timeline
2 articles · newest firstCoordGuard detects coordinated RAG retrieval poisoning via embedding geometry
Across four Natural Questions seeds, injections reached top-5 in 94.1% of targeted rows; e5 filtering cut exposure-conditional ASR to 0.167.
52
Appears with
- e5ai model · 2
- CoordGuardproduct · 1
- Qwen3-Embeddingai model · 1
- ReliabilityRAGproduct · 1
- DPRai model · 1
- RobustRAGproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.