arXiv (All)
open access
Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured benchmarks, which raises two concerns: output-level evaluation does
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
- Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure#1117767
- MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Models#1118966
- Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations#1011717
- When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations#1037020
- Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs#1142160
Record · ID 998156
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