DPO

Named by 2 kept items in this workspace.

1 items name it under classification.key entities and 1 under techniques.

The items that name it 2

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
paperas classification.key entities2026-10-15
Uncensored and Offensive Security AI Models Benchmark
repoas techniques2026-09-29It is written here as DPO (Direct Preference Optimization).
Preference-based fine-tuning technique

In every workspace you can read 8

AI

Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization
paper2026-10-27It is written here as Direct Preference Optimization (DPO).
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
paper2026-10-20It is written here as Direct preference optimization (DPO).
Open-sourcing AstaBrief, the fast report-generation model in Asta
article2026-10-02It is written here as Direct preference optimization (DPO).
Language Models for Text Classification: From Bag-of-Words to Jev
article2026-09-29It is written here as DPO (Direct Policy Optimization).
Uncensored and Offensive Security AI Models Benchmark
repo2026-09-29It is written here as DPO (Direct Preference Optimization).
FoundationAgents/awesome-foundation-agents
repo2026-05-07

Security

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
paper2026-10-15
Uncensored and Offensive Security AI Models Benchmark
repo2026-09-29It is written here as DPO (Direct Preference Optimization).

All techniques in this workspace.