# PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation

arXiv: https://arxiv.org/abs/2601.14903 · HTML: https://mlsanity.com/paper/2601.14903/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models](https://mlsanity.com/paper/2308.10755/) (2023)
- [Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards](https://mlsanity.com/paper/2506.00103/) (2025)
- [Reverse-Engineered Reasoning for Open-Ended Generation](https://mlsanity.com/paper/2509.06160/) (2025)
- [OpenDataLab: Empowering General Artificial Intelligence with Open Datasets](https://mlsanity.com/paper/2407.13773/) (2024)
- [Language Models can Self-Lengthen to Generate Long Texts](https://mlsanity.com/paper/2410.23933/) (2024)
- [MoonCast: High-Quality Zero-Shot Podcast Generation](https://mlsanity.com/paper/2503.14345/) (2025)
- [Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning](https://mlsanity.com/paper/2506.05760/) (2025)
- [PodAgent: A Comprehensive Framework for Podcast Generation](https://mlsanity.com/paper/2503.00455/) (2025)
- [PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation](https://mlsanity.com/paper/2510.00485/) (2025)

## Built on by (most cited first, 1 of 1)

- [On Improving Faithfulness of Podcasts from Documents](https://mlsanity.com/paper/2607.21961/) (2026)

## Abstract (arXiv)

Podcast script generation requires LLMs to synthesize structured, context-grounded dialogue from diverse inputs, yet systematic evaluation resources for this task remain limited. To bridge this gap, we introduce PodBench, a benchmark comprising 800 samples with inputs up to 21K tokens and complex multi-speaker instructions. We propose a multifaceted evaluation framework that integrates quantitative constraints with LLM-based quality assessment. Extensive experiments reveal that while proprietary models generally excel, open-source models equipped with explicit reasoning demonstrate superior robustness in handling long contexts and multi-speaker coordination compared to standard baselines. However, our analysis uncovers a persistent divergence where high instruction following does not guarantee high content substance. PodBench offers a reproducible testbed to address these challenges in long-form, audio-centric generation.