Self-Instruct: Aligning Language Models with Self-Generated Instructions · HackerPapers discussions

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by lxe

Tue, 14 Jan 2025 00:44:50 GMT

I think most of the instruction fine-tuning methods for oss models stem from Alpaca, so it should be included: https://crfm.stanford.edu/2023/03/13/alpaca.html And the one referenced in there on synthetic data generation: https://arxiv.org/abs/2212.10560

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by suprjami

Sat, 07 Dec 2024 09:42:14 GMT

It has existed for years: Self-Instruct: Aligning Language Models with Self-Generated Instructions https://arxiv.org/abs/2212.10560 airoboros: using large language models to fine-tune large language models https://github.com/jondurbin/airoboros

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by hapanin

Fri, 15 Dec 2023 15:59:24 GMT

Since nobody is actually recommending papers, here's an incomplete reading list that I sent out to some masters students I work with so they can understand the current research (academic) my little team is doing: Paper reference / main takeaways / link instructGPT / main concepts of instruction tuning / https://proceedings.neurips.cc/paper_files/paper/2022/hash/b... self-instruct / bootstrap off models own generations / https://arxiv.org/pdf/2212.10560.pdf Alpaca / how alpaca was trained / https://crfm.stanford.edu/2023/03/13/alpaca.html Llama 2 / probably the best chat model we can train on…

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by cubefox

Mon, 22 May 2023 19:32:39 GMT

There have been other approaches to make instruction tuning easier. This one proceeds largely on self generated synthetic data: https://arxiv.org/abs/2212.10560

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — HN submission

Sun, 02 Apr 2023 21:39:48 GMT

Self-Instruct: Aligning Language Model with Self Generated Instructions

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by jkeisling

Wed, 22 Mar 2023 13:02:47 GMT

For those skeptical of the above comment, this technique absolutely works and powers production-grade models like Anthropic’s Claude. There’s plenty of literature on this, but here are a couple papers that might be helpful for people doing their own training: - Constitutional AI: by Anthropic, an “RLAIF” technique that creates the preference model for “finding errors” based on a set of around 70 “principles” the AI uses to check its own output, not human feedback like in ChatGPT. This technique taught the Claude bot to avoid harmful output with few to no manual harmfulness labels!…

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by f_devd

Mon, 20 Mar 2023 22:54:18 GMT

Alpaca uses Self-Instruct[0] which is better than just the pre-training but I wouldn't expect it to be at the level of ChatGPT (RLHF) in terms of human-friendly prompting. OpenAssistant should make it close to ChatGPT (from GPT-3.5 version) if the LLaMA is as powerful as claimed. [0]: https://arxiv.org/abs/2212.10560

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

Self-Instruct: Aligning Language Models with Self-Generated Instructions — mentioned by eternalban

Mon, 13 Mar 2023 15:12:41 GMT

Self Instruct: https://arxiv.org/pdf/2212.10560.pdf https://github.com/yizhongw/self-instruct

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