LoReFT: Representation Finetuning for Language Models

Parameter-efficient fine-tuning or PeFT methods seek to adapt large language models via updates to a small number of weights. However, a majority of existing interpretability work has demonstrated that representations encode semantic rich information, suggesting that it might be a better and more powerful alternative to edit these representations. Pre-trained large models are often fine […]

The post LoReFT: Representation Finetuning for Language Models appeared first on Unite.AI.

adapt artificial intelligence edit encode fine-tuning finetuning fine tuning llm generative-ai however information interpretability language language models large language large language models large models machine learning natural language processing peft representation seek semantic small updates via work