arXiv (All)
open access
Many Perturbations, Shared Failure Dynamics: Tracing Direction-Sensitive Perturbation Influence in Language Models
Why can a task-preserving rewrite turn a correct answer into a failure while a larger internal change leaves the answer intact? We develop a direction-sensitive, readout-relative account of semantic fragility: heterogeneous language changes can share geometric and readout relationships without shari
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
- Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain#1202743
- Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations#1156399
- From Reconstruction to Fixation: Value and Ordering in Stateless Human–AI Systems#732758
- RIFT: Token Influence Follows the Path of Least Resistance#1327939
- A Fragility Spectrum for Recursive Language-Model Training#998701
Record · ID 1447676
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