pith. sign in

Safe DPO : A simple approach to direct preference optimization with enhanced safety

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Leveraging RAG for Training-Free Alignment of LLMs

cs.LG · 2026-05-11 · unverdicted · novelty 6.0

RAG-Pref is a training-free RAG-based alignment technique that conditions LLMs on contrastive preference samples during inference, yielding over 3.7x average improvement in agentic attack refusals when combined with offline methods across five LLMs.

citing papers explorer

Showing 1 of 1 citing paper.

  • Leveraging RAG for Training-Free Alignment of LLMs cs.LG · 2026-05-11 · unverdicted · none · ref 36

    RAG-Pref is a training-free RAG-based alignment technique that conditions LLMs on contrastive preference samples during inference, yielding over 3.7x average improvement in agentic attack refusals when combined with offline methods across five LLMs.