# CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models

arXiv: https://arxiv.org/abs/2405.13684 · HTML: https://mlsanity.com/paper/2405.13684/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 56 references that are in the map.
- First posted on arXiv 22 May 2024.

## Builds on (most cited first, 30 of 47)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)

## Built on by (most cited first, 18 of 18)

- [video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model](https://mlsanity.com/paper/2502.11775/) (2025)
- [LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2502.12359/) (2025)
- [HalluciNot: Hallucination Detection Through Context and Common Knowledge Verification](https://mlsanity.com/paper/2504.07069/) (2025)
- [Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information](https://mlsanity.com/paper/2506.11680/) (2025)
- [Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models](https://mlsanity.com/paper/2412.13702/) (2024)
- [Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models](https://mlsanity.com/paper/2409.10999/) (2024)
- [Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs](https://mlsanity.com/paper/2503.23219/) (2025)
- [Who can we trust? LLM-as-a-jury for Comparative Assessment](https://mlsanity.com/paper/2602.16610/) (2026)
- [SkillAggregation: Reference-free LLM-Dependent Aggregation](https://mlsanity.com/paper/2410.10215/) (2024)
- [Cross-Model Disagreement as a Label-Free Correctness Signal](https://mlsanity.com/paper/2603.25450/) (2026)
- [HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving](https://mlsanity.com/paper/2505.15793/) (2025)
- [LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks](https://mlsanity.com/paper/2409.12580/) (2024)
- [Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges](https://mlsanity.com/paper/2508.00454/) (2025)
- [Grounding the Ungrounded: A Spectral-Graph Framework for Quantifying Hallucinations in Multimodal LLMs](https://mlsanity.com/paper/2508.19366/) (2025)
- [Abductive Corroboration of Probabilistic AI Models for Forensic Synthetic Media Detection](https://mlsanity.com/paper/2607.05434/) (2026)
- [OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models](https://mlsanity.com/paper/2609.11244/) (2026)
- [Towards Systematic Qualification of Vision-Language Models for Automotive Perception Systems](https://mlsanity.com/paper/2609.25945/) (2026)
- [Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs](https://mlsanity.com/paper/2609.38070/) (2026)

## Abstract (arXiv)

Multimodal foundation models are prone to hallucination, generating outputs that either contradict the input or are not grounded by factual information. Given the diversity in architectures, training data and instruction tuning techniques, there can be large variations in systems' susceptibility to hallucinations. To assess system hallucination robustness, hallucination ranking approaches have been developed for specific tasks such as image captioning, question answering, summarization, or biography generation. However, these approaches typically compare model outputs to gold-standard references or labels, limiting hallucination benchmarking for new domains. This work proposes "CrossCheckGPT", a reference-free universal hallucination ranking for multimodal foundation models. The core idea of CrossCheckGPT is that the same hallucinated content is unlikely to be generated by different independent systems, hence cross-system consistency can provide meaningful and accurate hallucination assessment scores. CrossCheckGPT can be applied to any model or task, provided that the information consistency between outputs can be measured through an appropriate distance metric. Focusing on multimodal large language models that generate text, we explore two information consistency measures: CrossCheck-explicit and CrossCheck-implicit. We showcase the applicability of our method for hallucination ranking across various modalities, namely the text, image, and audio-visual domains. Further, we propose the first audio-visual hallucination benchmark, "AVHalluBench", and illustrate the effectiveness of CrossCheckGPT, achieving correlations of 98% and 89% with human judgements on MHaluBench and AVHalluBench, respectively.