Summary of Project Shadow: Symbolic Higher-order Associative Deductive Reasoning on Wikidata Using Lm Probing, by Hanna Abi Akl
Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing
by Hanna Abi Akl
First submitted to arxiv on: 27 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 introduces SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, which outperforms the baseline solution by 20% with a F1 score of 68.72% on the LM-KBC 2024 challenge, specifically in Wikidata triple completion. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper presents a new language model called SHADOW that uses a specific type of training called associative deductive reasoning to excel at a task involving constructing knowledge bases using data from Wikidata. The results show that SHADOW is better than the usual approach by a significant margin, making it a useful tool for this particular task. |
Keywords
» Artificial intelligence » F1 score » Language model
