arXiv (All)
open access
Controlling the Diversity-Quality Trade-Off of LLMs by Merging Models Before and After Alignment
Alignment is known to change the output characteristics of large language models (LLMs). Base models tend to generate more diverse outputs, whereas aligned models tend to produce higher-quality outputs. The appropriate balance between the two depends on the task. Existing methods either require cost
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
- Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs#820004
- LLM Probability Concentration: How Alignment Shrinks the Generative Horizon#1082952
- Cultural Alignment in Large Language Models Using Soft Prompt Tuning#1035281
- Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs#1296930
- Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another#1327731
Record · ID 1387288
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