No AI summary available for this article.
Why It Matters
We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-ended domains (in-the-wild chat, creative writing, planning for image generation, and protein design), Gacha Decoding significantly outperforms existing generation diversity approaches at equal quality (up to 2.4x Vendi over the next-best prior approach), reaching the same number of high-quality modes with over an order of magnitude fewer samples (11.0x) and discovering novel modes that no other approach surfaces. Our key insight is to treat dive...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.01382v1 · Indexed about 2 hours ago