arXiv (All)
open access
When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models
Cosine similarity is widely used to analyze transformer representations, implicitly assuming that similarity reflects task-relevant structure. We study when this assumption fails in dialogue-conditioned large language models. Across three 7-8B chat-tuned models, ambient cosine similarity substantial
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
- VoiceLongMemEval: Do Assistants Remember How You Sounded?#822035
- Syntactic patterns of Italo-Romance CP-layers in Transformers, ChatGPT and Deepseek: two case studies from Romansh and Neapolitan#732119
- Syntactic patterns of Italo-Romance CP-layers in Transformers, ChatGPT and Deepseek: two case studies from Romansh and Neapolitan#107694
- When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue#973357
- OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation#130759
Record · ID 1037205
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