Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?

ACL ARR 2025 February Submission1225 Authors

Abstract: In this work, we identify the "2D-Cheating" problem in 3D LLM evaluation, where these tasks might be easily solved by VLMs with rendered images of point clouds, exposing ineffective evaluation of 3D LLMs' unique 3D capabilities. We test VLM performance across multiple 3D LLM benchmarks and, using this as a reference, propose principles for better assessing genuine 3D understanding. We also advocate explicitly separating 3D abilities from 1D or 2D aspects when evaluating 3D LLMs.

Paper Type: Short

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: vision question answering, cross-modal application, multimodality

Contribution Types: Position papers

Languages Studied: English

Submission Number: 1225