SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.17115 · 2024

Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Despite the outstanding performance in multimodal tasks, Large Vision-Language Models (LVLMs) have been plagued by the issue of hallucination, i.e., generating content that is inconsistent with the corresponding visual inputs. While previous works have proposed various benchmarks to evaluate this issue, the quality of these evaluations remains unverified. We observe that some of these benchmarks may produce inconsistent evaluation results across repeated tests or fail to align with human evaluation. To address this, we propose a Hallucination benchmark Quality Measurement framework (HQM), which leverages specific indicators to assess both reliability and validity. Our empirical analysis using HQM reveals and pinpoints potential evaluation issues in existing benchmarks, exposing a critical gap in current hallucination evaluation. To bridge this gap, we propose HQH, a High-Quality Hallucination benchmark, which demonstrates superior reliability and validity under HQM, serving as a credible evaluation tool. Our large-scale evaluation of popular LVLMs on HQH reveals severe hallucination problems, which occur not only in the models' main answer to a question but also in additional analysis. This highlights the necessity for future model improvements to effectively mitigate hallucinations and reduce the associated security risks in real-world applications. Our benchmark is publicly available at https://github.com/HQHBench/HQHBench.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.17115")
get_code_for_paper("2406.17115")
have("2406.17115")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.17115.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.17115.svg)](https://syntology.ai/paper/2406.17115)

Connect an agent — have() is free.