0

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

SHADOW, a fine-tuned language model for associative deductive reasoning, outperforms the baseline in the LM-KBC 2024 challenge with a 20% improvement in F1 score.

Open
Year
2024
Venue
arXiv 2024
ArXiv
arxiv.org/abs/2408.14849
URL
arxiv.org/abs/2408.14849v2
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2408.14849v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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%.

Authors

1
Hanna Abi Akl