# Event-Grounded Question Answering over Long Audio via Structured Retrieval

arXiv: https://arxiv.org/abs/2602.14612 · HTML: https://mlsanity.com/paper/2602.14612/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities](https://mlsanity.com/paper/2406.11768/) (2024)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [Structure-Grounded Pretraining for Text-to-SQL](https://mlsanity.com/paper/2010.12773/) (2020)
- [Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL](https://mlsanity.com/paper/2406.08426/) (2024)
- [ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst](https://mlsanity.com/paper/2305.16103/) (2023)
- [Temporal Reasoning via Audio Question Answering](https://mlsanity.com/paper/1911.09655/) (2019)
- [AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs](https://mlsanity.com/paper/2510.07293/) (2025)
- [WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models](https://mlsanity.com/paper/2502.14727/) (2025)
- [FLAM: Frame-Wise Language-Audio Modeling](https://mlsanity.com/paper/2505.05335/) (2025)
- [Towards Weakly Supervised Text-to-Audio Grounding](https://mlsanity.com/paper/2401.02584/) (2024)
- [Audio Dialogues: Dialogues dataset for audio and music understanding](https://mlsanity.com/paper/2404.07616/) (2024)
- [Audio-Language Datasets of Scenes and Events: A Survey](https://mlsanity.com/paper/2407.06947/) (2024)
- [CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries](https://mlsanity.com/paper/2511.15131/) (2025)

## Built on by (most cited first, 2 of 2)

- [AS2D: Accelerating On-Demand Audio Understanding on Mobile Devices](https://mlsanity.com/paper/2609.37617/) (2026)
- [AMemOps: Evaluating Memory Updates in Long Audio Streams](https://mlsanity.com/paper/2610.18652/) (2026)

## Abstract (arXiv)

Answering natural-language questions over multi-hour audio requires reliable event recognition, temporal grounding, and efficient retrieval. We present LA-RAG (Long Audio Retrieval-Augmented Generation), a structured framework that converts audio into timestamped event records, stores them in an event database, and answers questions using intent-aware retrieval and LLM-based generation. LA-RAG supports two deployment settings: offline grounding mode, in which long recordings are pre-indexed for low-latency querying, and inference-time grounding mode, which performs query-conditioned grounding over shorter, open-ended clips. We evaluate LA-RAG on controlled 24-hour Home-IoT and Industrial-IoT benchmarks and on CASTELLA-QA, derived from real-world audio recordings. The results demonstrate effective long-audio question answering with low query-time latency after grounding and indexing. They also reveal a substantial gap between event detection and temporal localization in current large audio-language models, while showing that explicit timestamped grounding consistently improves temporal reasoning. These findings establish structured grounding and retrieval as a practical complement to generative audio-language models for deployment-oriented long-audio understanding.