Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC
Clay, A., Jiménez-Ruiz, E. 
ORCID: 0000-0002-9083-4599 & Madhyastha, P. ORCID: 0000-0002-4438-8161 (2025).
Noise or Nuance: An Investigation Into Useful Information and Filtering For LLM Driven AKBC.
In:
Joint Proceedings of the 3rd Workshop on Knowledge Base Construction from Pre-Trained Language Models and the 4th Challenge on Language Models for Knowledge Base Construction (KBC-LM+LM-KBC 2025).
3rd Workshop on Knowledge Base Construction from Pre-Trained Language Models and the 4th Challenge on Language Models for Knowledge Base Construction (KBC-LM+LM-KBC 2025), 2 Nov 2025, Nara, Japan.
Abstract
RAG and fine-tuning are prevalent strategies for improving the quality of LLM outputs. However, in constrained situations, such as that of the 2025 LM-KBC challenge, such techniques are restricted. In this work we investigate three facets of the triple completion task: generation, quality assurance, and LLM response parsing. Our work finds that in this constrained setting: additional information improves generation quality, LLMs can be effective at filtering poor quality triples, and the tradeoff between flexibility and consistency with LLM response parsing is setting dependent.
| Publication Type: | Conference or Workshop Item (Paper) |
|---|---|
| Additional Information: | © 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Departments: | School of Science & Technology School of Science & Technology > Department of Computer Science |
| SWORD Depositor: |
Available under License Creative Commons Attribution.
Download (923kB) | Preview
Export
Downloads
Downloads per month over past year
Metadata
MetadataActions (login required)
Admin Login