SHADOW 项目：利用 LM 探测在 Wikidata 上的符号高阶联想演绎推理

Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing

August 27, 2024

作者: Hanna Abi Akl

cs.AI

摘要

我们介绍了SHADOW，这是一个在中间任务上使用关联演绎推理训练的微调语言模型，并通过Wikidata三元组完成任务来衡量其性能。我们在LM-KBC 2024挑战赛上评估了SHADOW，并展示其以68.72%的F1分数优于基准解决方案20%。

English

We introduce SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, and measure its performance on a knowledge base construction task using Wikidata triple completion. We evaluate SHADOW on the LM-KBC 2024 challenge and show that it outperforms the baseline solution by 20% with a F1 score of 68.72%.