arXiv (All)
open access
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood. Prior work shows that aligned models can fail under jailbreak prompts, alternative encodings, and cross-lingual transfer, ye
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
- Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders#1104421
- Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection#793473
- Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection#789469
- Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs#1036827
- Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin#394468
Record · ID 1117048
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