pith. sign in

arxiv: 2508.14080 · v1 · pith:XAABTAWFnew · submitted 2025-08-12 · 💻 cs.LG

KnowDR-REC: A Benchmark for Referring Expression Comprehension with Real-World Knowledge

classification 💻 cs.LG
keywords multimodalbenchmarkexpressionmodelsreasoningfine-grainedgroundingknowdr-rec
0
0 comments X
read the original abstract

Referring Expression Comprehension (REC) is a popular multimodal task that aims to accurately detect target objects within a single image based on a given textual expression. However, due to the limitations of earlier models, traditional REC benchmarks either rely solely on intra-image cues or lack sufficiently fine-grained instance annotations, making them inadequate for evaluating the reasoning capabilities of Multi-modal Large Language Models (MLLMs). To address this gap, we propose a new benchmark, KnowDR-REC, characterized by three key features: Firstly, it is built upon real-world knowledge, requiring fine-grained multimodal reasoning across text and image. Secondly, the dataset includes elaborately constructed negative samples via fine-grained expression editing, designed to evaluate a model's robustness and anti-hallucination ability. Lastly, we introduce three novel evaluation metrics to systematically explore the model's internal reasoning process. We evaluate 16 state-of-the-art multimodal models on KnowDR-REC, with experimental results showing that existing MLLMs still struggle with knowledge-driven visual grounding tasks. Furthermore, we observe a decoupling between textual understanding and visual grounding in MLLMs, where many models are significantly influenced by memorized shortcut correlations, which severely affect their behavior on our benchmark and hinder genuine multimodal reasoning. We anticipate that the proposed benchmark will inspire future research towards developing more robust, interpretable, and knowledge-intensive visual grounding frameworks, driving the development of more reliable and robust multimodal systems for complex real-world scenarios.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs

    cs.CV 2026-06 unverdicted novelty 7.0

    FindIt is the first comprehensive benchmark for evaluating generalist MLLMs on promptable object detection, referring expression detection, instance-level detection, and video detection with standardized parsable outputs.