arXiv (All)
open access
Tracing Stereotypes from Representation to Output in Multilingual LLMs
Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is represented or how it affects the output. To investigate these internal mechanisms, we compare linear probing, attribution patching, sparse autoencoder
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
- A Repeated-Measurement Study for Cultural Analytics of English Song Lyrics Using Five Large Language Models#927718
- When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations#1037020
- An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations#2611
- Gender Bias in Vision-Language In-Context Learning#1064226
- The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance#1061393
Record · ID 985686
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