Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Hanna Abi Akl

TL;DR

SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, is introduced and its performance on a knowledge base construction task using Wikidata triple completion is measured.

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%.

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

TL;DR

SHADOW, a fine-tuned language model trained on an intermediate task using associative deductive reasoning, is introduced and its performance on a knowledge base construction task using Wikidata triple completion is measured.

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%.
Paper Structure (8 sections, 1 figure, 4 tables)

This paper contains 8 sections, 1 figure, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Experiments
  4. Dataset
  5. Model
  6. Setup
  7. Results
  8. Conclusion

Figures (1)

  • Figure 1: Experimental setup.