Paper ID: 2408.14849

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

Hanna Abi Akl

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%.

Submitted: Aug 27, 2024