# CLAIR-A: Leveraging Large Language Models to Judge Audio Captions

arXiv: https://arxiv.org/abs/2409.12962 · HTML: https://mlsanity.com/paper/2409.12962/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [Improved Image Captioning via Policy Gradient optimization of SPIDEr](https://mlsanity.com/paper/1612.00370/) (2016)
- [CLAIR: Evaluating Image Captions with Large Language Models](https://mlsanity.com/paper/2310.12971/) (2023)
- [Automated Audio Captioning with Recurrent Neural Networks](https://mlsanity.com/paper/1706.10006/) (2017)
- [Can Audio Captions Be Evaluated with Image Caption Metrics?](https://mlsanity.com/paper/2110.04684/) (2021)
- [ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds](https://mlsanity.com/paper/2403.18572/) (2024)

## Built on by (most cited first, 5 of 5)

- [Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2411.16863/) (2024)
- [ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection](https://mlsanity.com/paper/2505.11079/) (2025)
- [From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training](https://mlsanity.com/paper/2509.20072/) (2025)
- [Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation](https://mlsanity.com/paper/2607.13477/) (2026)
- [CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation](https://mlsanity.com/paper/2603.19615/) (2026)

## Abstract (arXiv)

The Automated Audio Captioning (AAC) task asks models to generate natural language descriptions of an audio input. Evaluating these machine-generated audio captions is a complex task that requires considering diverse factors, among them, auditory scene understanding, sound-object inference, temporal coherence, and the environmental context of the scene. While current methods focus on specific aspects, they often fail to provide an overall score that aligns well with human judgment. In this work, we propose CLAIR-A, a simple and flexible method that leverages the zero-shot capabilities of large language models (LLMs) to evaluate candidate audio captions by directly asking LLMs for a semantic distance score. In our evaluations, CLAIR-A better predicts human judgements of quality compared to traditional metrics, with a 5.8% relative accuracy improvement compared to the domain-specific FENSE metric and up to 11% over the best general-purpose measure on the Clotho-Eval dataset. Moreover, CLAIR-A offers more transparency by allowing the language model to explain the reasoning behind its scores, with these explanations rated up to 30% better by human evaluators than those provided by baseline methods. CLAIR-A is made publicly available at https://github.com/DavidMChan/clair-a.