Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agarwal, Dhruv, Das, Rajarshi, Khosla, Sopan, Gangadharaiah, Rashmi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911286789406720
author Agarwal, Dhruv
Das, Rajarshi
Khosla, Sopan
Gangadharaiah, Rashmi
author_facet Agarwal, Dhruv
Das, Rajarshi
Khosla, Sopan
Gangadharaiah, Rashmi
contents We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems. BYOKG draws inspiration from the remarkable ability of humans to comprehend information present in an unseen KG through exploration -- starting at random nodes, inspecting the labels of adjacent nodes and edges, and combining them with their prior world knowledge. In BYOKG, exploration leverages an LLM-backed symbolic agent that generates a diverse set of query-program exemplars, which are then used to ground a retrieval-augmented reasoning procedure to predict programs for arbitrary questions. BYOKG is effective over both small- and large-scale graphs, showing dramatic gains in QA accuracy over a zero-shot baseline of 27.89 and 58.02 F1 on GrailQA and MetaQA, respectively. On GrailQA, we further show that our unsupervised BYOKG outperforms a supervised in-context learning method, demonstrating the effectiveness of exploration. Lastly, we find that performance of BYOKG reliably improves with continued exploration as well as improvements in the base LLM, notably outperforming a state-of-the-art fine-tuned model by 7.08 F1 on a sub-sampled zero-shot split of GrailQA.
format Preprint
id arxiv_https___arxiv_org_abs_2311_07850
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA
Agarwal, Dhruv
Das, Rajarshi
Khosla, Sopan
Gangadharaiah, Rashmi
Computation and Language
Artificial Intelligence
Databases
Machine Learning
We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems. BYOKG draws inspiration from the remarkable ability of humans to comprehend information present in an unseen KG through exploration -- starting at random nodes, inspecting the labels of adjacent nodes and edges, and combining them with their prior world knowledge. In BYOKG, exploration leverages an LLM-backed symbolic agent that generates a diverse set of query-program exemplars, which are then used to ground a retrieval-augmented reasoning procedure to predict programs for arbitrary questions. BYOKG is effective over both small- and large-scale graphs, showing dramatic gains in QA accuracy over a zero-shot baseline of 27.89 and 58.02 F1 on GrailQA and MetaQA, respectively. On GrailQA, we further show that our unsupervised BYOKG outperforms a supervised in-context learning method, demonstrating the effectiveness of exploration. Lastly, we find that performance of BYOKG reliably improves with continued exploration as well as improvements in the base LLM, notably outperforming a state-of-the-art fine-tuned model by 7.08 F1 on a sub-sampled zero-shot split of GrailQA.
title Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA
topic Computation and Language
Artificial Intelligence
Databases
Machine Learning
url https://arxiv.org/abs/2311.07850