arXiv (All)
open access
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A task-trained rank-8 LoRA at one early layer extends this computation with all model weights frozen. Qwen3-8B improves f
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
- Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers#432586
- Structure is not mechanism: high-gain gated-FFN rows across text and genomic foundation models#1011331
- A Unified Perspective on the Dynamics of Deep Transformers#1120649
- Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction#1115912
- Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation#1104422
Record · ID 1131786
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