Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models · HackerPapers discussions

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models — mentioned by arthurcolle

Sun, 21 Jan 2024 00:38:21 GMT

A recent paper goes into this right? Self-Play Fine Tuning for Weak to Strong Generalization: https://arxiv.org/pdf/2401.01335.pdf Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the prospect of growing a strong LLM out of a weak one without the need for acquiring additional human annotated data. We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN), which starts from a supervised fine-tuned model. At the heart of SPIN lies a self-play mechanism, where the…

Paper and discussion history. A mention is not an endorsement.

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models — mentioned by ignoramous

Thu, 11 Jan 2024 21:58:26 GMT

See also Self-Play Fine-Tuning (SPIN) https://arxiv.org/abs/2401.01335 that (per authors) tunes as well as Direct Preference Optimization (DPO).

Paper and discussion history. A mention is not an endorsement.

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models — HN submission

Wed, 03 Jan 2024 20:46:59 GMT

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

41 points; 12 discussion replies on HN. Paper and source history. A submission is not an endorsement.