Summary of Fidelis: Faithful Reasoning in Large Language Model For Knowledge Graph Question Answering, by Yuan Sui et al.
FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
by Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, Bryan Hooi
First submitted to arxiv on: 22 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a unified framework, FiDeLiS, to improve the factuality of large language model responses by leveraging knowledge graphs as external knowledge sources. The framework combines step-wise beam search with deductive scoring and a Path-rag module to pre-select candidate answers, reducing computational costs. This approach outperforms strong baselines in both factuality and interpretability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FiDeLiS is designed to help large language models (LLMs) generate accurate responses by using knowledge graphs (KGs) as a reference point. The model uses step-wise beam search to find the best answer, and then validates each reasoning step to make sure it’s correct. This approach reduces errors and makes it easier to understand how the model arrived at its answer. |
Keywords
» Artificial intelligence » Large language model » Rag
