paper-with-me

홈 › Papers

OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models

2025-07-25 · Monika Wysoczańska, Shyamal Buch, Anurag Arnab, Cordelia Schmid arxiv

Large vision-language models (VLMs) often struggle to generate long and factual captions. However, traditional measures for hallucination and factuality are not well suited for evaluating longer, more diverse captions and in settings where ground-truth human-annotated captions are unavailable. We introduce OV-Fact, a novel method for measuring caption factuality of long captions that leverages open-vocabulary visual grounding and tool-based verification without depending on human annotations. Our method improves agreement with human judgments and captures both caption descriptiveness (recall) and factual precision in the same metric. Furthermore, unlike previous metrics, our reference-free method design enables new applications towards factuality-based data filtering. We observe models trained on an OVFact-filtered (2.5-5x less) subset of a large-scale, noisy (VLM-generated) pretraining set meaningfully improve factuality precision without sacrificing caption descriptiveness across a range of downstream long caption benchmarks.

📄 PDF Abstract BibTeX arXiv:2507.19262

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

2026-07-21 · Xilun Chen, Zhaleh Feizollahi, Ross Goodwin, Seungwhan Moon 외 hf

Evaluating the factuality of long-form generations has focused predominantly on precision, measuring whether the claims a model makes are correct. The dominant decompose-search-verify pipeline catches incorrect claims we…

AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains

2026-01-21 · Adam Szelestey, Sofie van Engelen, Tianhao Huang, Justin Snelders 외 arxiv

Hallucination in large language models (LLMs) remains an acute concern, contributing to the spread of misinformation and diminished public trust, particularly in high-risk domains. Among hallucination types, factuality i…

Adversarial Attack

Fine-tuning Language Models for Factuality

2023-11-14 · Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning 외

The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing …

Fact CheckingMisconceptionsMisinformationRetrieval

Long-form factuality in large language models

2024-03-27 · Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu 외

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT…

16kForm

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation

2024-11-25 · Sanjana Ramprasad, Byron C. Wallace

Modern LLMs can now produce highly readable abstractive summaries, to the point where traditional automated metrics for evaluating summary quality, such as ROUGE, have become saturated. However, LLMs still sometimes intr…