Artificial Intelligence · 25.08.2026, 11:31 UTC
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.CL ↗ |
| Veröffentlicht | 25.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks and architectures. We introduce Coherentist Probabilistic Compositionalism (CPC), an interpretive framework that grounds transformer computation in coherentist theories of interpretation and describes it through four operator roles. Alignment identifies candidate relations, unification integrates supporting information, suppression reduces incompatible alternatives, and routing carries selected information to the output. Across 15 models from five architecture families, the suppression, unification, and routing weight-space signatures correlate with held-out activation-level role measures above random baselines. Suppression is more stable across tasks than unification. Ablating alignment heads reduces downstream suppressive activity beyond a random-head control in 10 models, but similar effects on no-conflict prompts indicate a general upstream dependency, not contradiction-specific coupling. Explicit contradictions significantly shift a layerwise coherence proxy in 14 models; after removing shared residual covariance, the gap has the predicted direction in every model. Base and instruction-tuned variants preserve induction-head score structure ($r{\geq}0.98$) without a consistent shift of operator signatures towards later layers. These results support CPC as a shared vocabulary for comparing transformer mechanisms while showing that their depth and geometric expression …
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks
- info Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
- info The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation
- info SelFusion: Self-distillation for Diffusion Language Models