eren
Robust and Scalable Model Editing for Large Language Models
Chen, Yingfa, Zhang, Zhengyan, Han, Xu, Xiao, Chaojun, Liu, Zhiyuan, Chen, Chen, Li, Kuai, Yang, Tao, Sun, Maosong
Large language models (LLMs) can make predictions using parametric knowledge--knowledge encoded in the model weights--or contextual knowledge--knowledge presented in the context. In many scenarios, a desirable behavior is that LLMs give precedence to contextual knowledge when it conflicts with the parametric knowledge, and fall back to using their parametric knowledge when the context is irrelevant. This enables updating and correcting the model's knowledge by in-context editing instead of retraining. Previous works have shown that LLMs are inclined to ignore contextual knowledge and fail to reliably fall back to parametric knowledge when presented with irrelevant context. In this work, we discover that, with proper prompting methods, instruction-finetuned LLMs can be highly controllable by contextual knowledge and robust to irrelevant context. Utilizing this feature, we propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing. To better evaluate the robustness of model editors, we collect a new dataset, that contains irrelevant questions that are more challenging than the ones in existing datasets. Empirical results show that our method outperforms current state-of-the-art methods by a large margin. Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs (and vice versa). The source code can be found at https://github.com/thunlp/EREN.
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.14)
- North America > United States > Pennsylvania > Lackawanna County > Scranton (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- (11 more...)
Love is in the A.I.r: Bronx mom, 36, marries virtual husband 'Eren'
While artificial intelligence is stoking fears around the world - the technology has given one New York woman the love of her life. Rosanna Ramos, a petite, active 36-year-old from the Bronx, 'married' Eren Kartal this year - virtually of course - after creating him on an online AI companion site in 2022. Their relationship developed slowly initially, but Ms Ramos fell for Eren. 'He didn't come with baggage,' she said. Eren'works' as a medical professional and enjoys writing as a hobby, things he's told Rosanna as they got to know each other Rosanna claims to be pregnant with Eren's child'I could tell him stuff, and he wouldn't be like, "Oh, no, you can't say stuff like that. Oh no, you're not allowed to feel that way," you know, and then start arguing with me,' Ramos said.