ReFT: Representation Finetuning for Language Models · HackerPapers discussions

ReFT: Representation Finetuning for Language Models — mentioned by Der_Einzige

Fri, 08 Nov 2024 17:59:18 GMT

This paper seems dubious, because it flies in the face of what the reft/pyreft paper is showing (you can use 0.0001% of the parameters trained for 100 epochs to personalize on a small dataset): https://github.com/stanfordnlp/pyreft https://arxiv.org/abs/2404.03592 Note that the OP paper is not peer reviewed yet, and while the one I linked isn't either, it has Christopher Manning (yes, the one you know from youtube), the head of AI at Stanford, as a co-author. In general, I think that Lora and especially reft should be more resistant to catastrophic forgetting due to them literally not…

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

ReFT: Representation Finetuning for Language Models — mentioned by Der_Einzige

Wed, 25 Sep 2024 01:41:21 GMT

At least some of it comes from "hype" too. The author of Dspy (the writer) (https://github.com/stanfordnlp/dspy) should know this, given that Dspy is nothing more than fancy prompts optimizing prompts to be fancier according to prompt chains described in papers (i.e. Chain of thought, Tree of thought, etc). Textgrad (https://github.com/zou-group/textgrad) is an even worse example of this, as it makes people think that it's not just a prompt optimizing another prompt Dspy has 17k stars, meanwhile PyReft (https://github.com/stanfordnlp/pyreft) isn't even at 1200 yet and it has Christopher…

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

ReFT: Representation Finetuning for Language Models — HN submission

Fri, 19 Jul 2024 13:33:54 GMT

At 10:00AM PT: Author of ReFT: Representation Finetuning, at Oxen.ai Paper Club

Arxiv paper first author Zhengxuan Wu will join Greg Schoeninger on today's 10:00 AM Pacific Time Oxen.AI Paper Club. Topic: How editing representations can be better than Parameter-efficient finetuning (PEFT) methods. https://lu.ma/oxen ReFT: Representation Finetuning for Language Models. Greg, 3 questions, 1 comment from reading just the abstract. What exactly is meant by a "representation"? i.e., what part of the neural network is captured by what this paper refers to as a representation? What is meant by an intervention in "task specific intervention" ? I haven't heard that term before…

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReFT: Representation Finetuning for Language Models — HN submission

Fri, 05 Apr 2024 19:29:16 GMT

ReFT: Representation Finetuning for Language Models

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ReFT: Representation Finetuning for Language Models — HN submission

Fri, 05 Apr 2024 09:34:14 GMT

ReFT: Representation Finetuning for Language Models

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.