SHADOW計畫：利用LM探測在Wikidata上進行符號高階聯想演繹推理

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

我們介紹了SHADOW，這是一個在中間任務上使用聯想演繹推理訓練的微調語言模型，並測試其在知識庫構建任務中使用Wikidata三元組完成的表現。我們在LM-KBC 2024挑戰中評估了SHADOW，並展示其以68.72%的F1分數優於基準解決方案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%.