CLAIIRAug 3, 2024

PLUGH: A Benchmark for Spatial Understanding and Reasoning in Large Language Models

arXiv:2408.04648v12 citationsh-index: 2Has Code
Originality Synthesis-oriented
AI Analysis

This addresses the need for better spatial reasoning evaluation in LLMs, though it is incremental as it builds on existing benchmarking efforts.

The authors introduced PLUGH, a benchmark with 5 tasks and 125 texts from 48 games to evaluate spatial understanding in LLMs, finding that while some commercial models perform well, open-sourced ones are competitive but all have significant room for improvement.

We present PLUGH (https://www.urbandictionary.com/define.php?term=plugh), a modern benchmark that currently consists of 5 tasks, each with 125 input texts extracted from 48 different games and representing 61 different (non-isomorphic) spatial graphs to assess the abilities of Large Language Models (LLMs) for spatial understanding and reasoning. Our evaluation of API-based and open-sourced LLMs shows that while some commercial LLMs exhibit strong reasoning abilities, open-sourced competitors can demonstrate almost the same level of quality; however, all models still have significant room for improvement. We identify typical reasons for LLM failures and discuss possible ways to deal with them. Datasets and evaluation code are released (https://github.com/altsoph/PLUGH).

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes