Summary of Multi-hop Question Answering Under Temporal Knowledge Editing, by Keyuan Cheng et al.
Multi-hop Question Answering under Temporal Knowledge Editing
by Keyuan Cheng, Gang Lin, Haoyang Fei, Yuxuan zhai, Lu Yu, Muhammad Asif Ali, Lijie Hu, Di Wang
First submitted to arxiv on: 30 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 proposed framework, TEMPLE-MQA, aims to improve multi-hop question answering under knowledge editing (KE) by addressing the limitation of existing models in dealing with questions containing explicit temporal contexts. The approach constructs a time-aware graph (TAG) and uses inference paths, structural retrieval, and joint reasoning stages to effectively discern temporal contexts within the question query. Experiments on benchmark datasets demonstrate that TEMPLE-MQA significantly outperforms baseline models. The framework also contributes a new dataset, TKEMQA, which serves as a benchmark for MQA with temporal scopes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary TEMPLE-MQA is a new way to answer questions that require multiple steps and involve changing information over time. This approach helps large language models understand questions that mention specific times or events. The model creates a special graph to store knowledge about editing and then uses this graph to figure out the correct answers. The results show that TEMPLE-MQA does much better than other methods. It also introduces a new dataset, TKEMQA, which will help researchers test their own models on similar tasks. |
Keywords
* Artificial intelligence * Inference * Question answering
