Summary of Editing Conceptual Knowledge For Large Language Models, by Xiaohan Wang et al.
Editing Conceptual Knowledge for Large Language Models
by Xiaohan Wang, Shengyu Mao, Ningyu Zhang, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen
First submitted to arxiv on: 10 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Databases (cs.DB); Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper pioneers the investigation of editing conceptual knowledge for Large Language Models (LLMs) by constructing a novel benchmark dataset ConceptEdit and establishing a suite of new metrics for evaluation. It reveals that existing editing methods can modify concept-level definition to some extent, but also have the potential to distort related instantial knowledge in LLMs, leading to poor performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores whether Large Language Models (LLMs) can modify concepts. Researchers created a special dataset and metrics to test this. They found that current editing methods can change concept definitions, but sometimes mess up other related information, making the model perform poorly. |
