# CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation

arXiv: https://arxiv.org/abs/2603.19615 · HTML: https://mlsanity.com/paper/2603.19615/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [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)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Improved Image Captioning via Policy Gradient optimization of SPIDEr](https://mlsanity.com/paper/1612.00370/) (2016)
- [FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model](https://mlsanity.com/paper/2406.06004/) (2024)
- [CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models](https://mlsanity.com/paper/2310.08753/) (2023)
- [Can Audio Captions Be Evaluated with Image Caption Metrics?](https://mlsanity.com/paper/2110.04684/) (2021)
- [MiDashengLM: Efficient Audio Understanding with General Audio Captions](https://mlsanity.com/paper/2508.03983/) (2025)
- [Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding](https://mlsanity.com/paper/2506.07233/) (2025)
- [PAM: Prompting Audio-Language Models for Audio Quality Assessment](https://mlsanity.com/paper/2402.00282/) (2024)
- [Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training](https://mlsanity.com/paper/2408.07919/) (2024)
- [M2D-CLAP: Exploring General-purpose Audio-Language Representations Beyond CLAP](https://mlsanity.com/paper/2503.22104/) (2025)
- [AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering](https://mlsanity.com/paper/2601.14728/) (2026)
- [BRACE: A Benchmark for Robust Audio Caption Quality Evaluation](https://mlsanity.com/paper/2512.10403/) (2025)
- [CLAIR-A: Leveraging Large Language Models to Judge Audio Captions](https://mlsanity.com/paper/2409.12962/) (2024)
- [RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio](https://mlsanity.com/paper/2506.23582/) (2025)

## Abstract (arXiv)

While Large Audio-Language Models (LALMs) have advanced audio captioning, robust evaluation remains difficult. Reference-based metrics are expensive and often fail to assess acoustic fidelity, while Contrastive Language-Audio Pretraining (CLAP)-based approaches frequently overlook syntactic errors and fine-grained details. We propose CAF-Score, a reference-free metric that calibrates CLAP's coarse-grained semantic alignment with the fine-grained comprehension and syntactic awareness of LALMs. By combining contrastive audio-text embeddings with LALM reasoning, CAF-Score effectively detects syntactic inconsistencies and subtle hallucinations. Experiments on the BRACE benchmark demonstrate that our approach achieves the highest correlation with human judgments, even outperforming reference-based baselines in challenging scenarios. These results highlight the efficacy of CAF-Score for reference-free audio captioning evaluation. Code and results are available at https://github.com/inseong00/CAF-Score.