arXiv (All)
open access
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows each reasoning step to attend to the full context, enabling
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation#1417820
- Generative Reality: A Model of Reality as Sequential Token Generation with Conscious Readahead#84294
- Unconscious cognitive filling: why AI emergence is a property of human–AI systems, not models alone#725076
- Are Generative Models Structural Representations?#92464
- Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners#1357045
Record · ID 1424772
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive