# FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models

arXiv: https://arxiv.org/abs/2311.01477 · HTML: https://mlsanity.com/paper/2311.01477/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 2 Nov 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [MultiModal-GPT: A Vision and Language Model for Dialogue with Humans](https://mlsanity.com/paper/2305.04790/) (2023)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [DenseCap: Fully Convolutional Localization Networks for Dense Captioning](https://mlsanity.com/paper/1511.07571/) (2015)
- [Visual Storytelling](https://mlsanity.com/paper/1604.03968/) (2016)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [Multimodal Conversational AI: A Survey of Datasets and Approaches](https://mlsanity.com/paper/2205.06907/) (2022)

## Built on by (most cited first, 30 of 46)

- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback](https://mlsanity.com/paper/2404.05046/) (2024)
- [Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination](https://mlsanity.com/paper/2411.12591/) (2024)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [Reference-free Hallucination Detection for Large Vision-Language Models](https://mlsanity.com/paper/2408.05767/) (2024)
- [Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training](https://mlsanity.com/paper/2404.14604/) (2024)
- [TLDR: Token-Level Detective Reward Model for Large Vision Language Models](https://mlsanity.com/paper/2410.04734/) (2024)
- [RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks](https://mlsanity.com/paper/2511.01758/) (2025)
- [GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity](https://mlsanity.com/paper/2508.19972/) (2025)
- [Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models](https://mlsanity.com/paper/2505.07001/) (2025)
- [Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models](https://mlsanity.com/paper/2406.17115/) (2024)
- [Cross-Image Contrastive Decoding: Precise, Lossless Suppression of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2505.10634/) (2025)
- [Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning](https://mlsanity.com/paper/2403.10492/) (2024)
- [Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs](https://mlsanity.com/paper/2511.08409/) (2025)
- [AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2403.08542/) (2024)
- [HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs](https://mlsanity.com/paper/2512.07687/) (2025)
- [Detailed Object Description with Controllable Dimensions](https://mlsanity.com/paper/2411.19106/) (2024)
- [Improving Alignment in LVLMs with Debiased Self-Judgment](https://mlsanity.com/paper/2508.20655/) (2025)
- [Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine](https://mlsanity.com/paper/2506.20876/) (2025)
- [SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision](https://mlsanity.com/paper/2508.03177/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [A Study on the Framework for Evaluating the Ethics and Trustworthiness of Generative AI](https://mlsanity.com/paper/2509.00398/) (2025)
- [ClipTTT: CLIP-Guided Test-Time Training Helps LVLMs See Better](https://mlsanity.com/paper/2603.26486/) (2026)
- [BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning](https://mlsanity.com/paper/2605.07394/) (2026)
- [Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -](https://mlsanity.com/paper/2504.12137/) (2025)
- [Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding](https://mlsanity.com/paper/2510.18321/) (2025)
- [PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions](https://mlsanity.com/paper/2510.19060/) (2025)
- [Seeing Through the MiRAGE: Evaluating Multimodal Retrieval Augmented Generation](https://mlsanity.com/paper/2510.24870/) (2025)
- [FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering](https://mlsanity.com/paper/2601.00269/) (2026)
- [One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs](https://mlsanity.com/paper/2601.23041/) (2026)

## Abstract (arXiv)

We introduce FaithScore (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The FaithScore evaluation first identifies sub-sentences containing descriptive statements that need to be verified, then extracts a comprehensive list of atomic facts from these sub-sentences, and finally conducts consistency verification between fine-grained atomic facts and the input image. Meta-evaluation demonstrates that our metric highly correlates with human judgments of faithfulness. We collect two benchmark datasets (i.e. LLaVA-1k and MSCOCO-Cap) for evaluating LVLMs instruction-following hallucinations. We measure hallucinations in state-of-the-art LVLMs with FaithScore on the datasets. Results reveal that current systems are prone to generate hallucinated content unfaithful to the image, which leaves room for future improvements. We hope our metric FaithScore can help evaluate future LVLMs in terms of faithfulness and provide insightful advice for enhancing LVLMs' faithfulness.