---
title: "WavRAG — paper by Chen et al. (2025) — summary and ideas"
description: "The authors present WavRAG, which they describe as the first RAG framework that handles audio… 47 references, cited by 13 papers here."
authors: ["Yifu Chen", "Shengpeng Ji", "Haoxiao Wang", "Ziqing Wang", "Siyu Chen", "Jinzheng He", "Jin Xu", "Zhou Zhao"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.613/"
doi: "10.18653/v1/2025.acl-long.613"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2025-wavrag-audio-integrated-retrieval-augmented/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2025-wavrag-audio-integrated-retrieval-augmented/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models

# WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models

**Authors:** [Yifu Chen](https://md.research.elamur.ai/free/en/authors/yifu-chen/), [Shengpeng Ji](https://md.research.elamur.ai/free/en/authors/shengpeng-ji/), Haoxiao Wang, [Ziqing Wang](https://md.research.elamur.ai/free/en/authors/ziqing-wang/), [Siyu Chen](https://md.research.elamur.ai/free/en/authors/siyu-chen/), [Jinzheng He](https://md.research.elamur.ai/free/en/authors/jinzheng-he/), [Jin Xu](https://md.research.elamur.ai/free/en/authors/jin-xu/) and [Zhou Zhao](https://md.research.elamur.ai/free/en/authors/zhou-zhao/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.613/) · [PDF](https://aclanthology.org/2025.acl-long.613.pdf) · [DOI 10.18653/v1/2025.acl-long.613](https://doi.org/10.18653/v1/2025.acl-long.613) · [OpenAlex](https://openalex.org/W4412945327)

**Citations:** 9 citations (OpenAlex, 2026-10-14) · [13](https://md.research.elamur.ai/free/en/papers/chen-2025-wavrag-audio-integrated-retrieval-augmented/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most retrieval-augmented generation (RAG) systems assume text input, so spoken dialogue models usually reach them through a cascaded ASR step. That detour has several costs. It discards non-speech and acoustic cues, lets transcription mistakes propagate, adds latency, and leaves audio-only knowledge outside the knowledge base.

The authors present WavRAG, which they describe as the first RAG framework that handles audio natively and end to end. Its retriever, WavRetriever, is built on Qwen2-Audio. The audio encoder is kept frozen, while the projection layer and LLM backbone are trained with a contrastive objective. This yields a single embedding space for speech, general sounds, text and mixed inputs. Retrieval runs over a hybrid text-audio knowledge base, and Chain-of-Thought prompting helps the generator combine the retrieved items.

Compared with ASR-Text pipelines (Whisper + BGE), WavRAG matches their retrieval accuracy while running about ten times faster on average, and it clearly wins on combined audio+text retrieval. The work matters because it extends RAG to audio knowledge beyond speech.

## Key points
- WavRetriever turns Qwen2-Audio-7B-Instruct into an embedding model through contrastive training. In ablation, this improves Recall@1 by +0.3075 to +0.3437 and nDCG@10 by up to +0.4169 over the untuned model.
- Retrieval speedups over BGE models paired with Whisper range from roughly 5x to more than 14x (about 10x on average). The largest accuracy gains appear in the Audio+Text-to-Audio+Text setting.
- Giving the generator raw audio beats TextRAG. With GPT-4o on HotpotQA, top-1 EM rises from 0.3124 to 0.4019, and gains are also reported on SLUE-SQA-5 and with QwenAudio.
- Adding Chain-of-Thought (WavRAG-CoT) gives further gains:
  - SLUE-SQA-5 top-1 EM: 0.3904 → 0.4520 (GPT-4o).
  - FactScore on the custom multimodal dataset: 0.5732 → 0.6412.
  - CoT also reduces the performance drop seen when moving from Top-2 to Top-3 retrieved items.
- Human raters assessed 700 samples of the generated audio-related knowledge on four criteria: grammar, factuality, relevance and helpfulness. Most samples received top scores and were judged helpful. Effects on prosody and emotional tone are left for future work.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 168 works · 15,386 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 172 works · 12,988 citations
- [Beijing University of Technology](https://md.research.elamur.ai/free/en/universities/beijing-university-of-technology/) — University, Beijing, China · 13 works · 1,910 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (3): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 480 works

## Cite

Cite as: Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu and Zhou Zhao. 2025. WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{chen2025wavrag,
  title = {{WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models}},
  author = {Yifu Chen, Shengpeng Ji, Haoxiao Wang, Ziqing Wang, Siyu Chen, Jinzheng He, Jin Xu and Zhou Zhao},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.613},
  url = {https://doi.org/10.18653/v1/2025.acl-long.613}
}
```

- [← previous VISA: Retrieval Augmented Generation with Visual Source Attribution](https://md.research.elamur.ai/free/en/papers/ma-2025-visa-retrieval-augmented-generation-visual/)
- [next → AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy](https://md.research.elamur.ai/free/en/papers/liu-2025-acereason-nemotron-1-1-advancing/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

47 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, and Christian Frank. 2023. Musiclm: Generating music from text. Preprint, arXiv:2301.11325. — [arXiv:2301.11325](https://arxiv.org/abs/2301.11325) [find](https://scholar.google.com/scholar?q=Andrea+Agostinelli%2C+Timo+I%2E+Denk%2C+Zal%C3%A1n+Borsos%2C+Jesse+Engel%2C+Mauro+Verzetti%2C+Antoine+Caillon%2C+Qingqing+Huang%2C+Aren+Jansen%2C+Adam+Roberts%2C+Marco+Tagliasacchi%2C+Matt+Sharifi%2C+Neil+Zeghidour%2C+and+Christian)
2. Keyu An, Qian Chen, Chong Deng, Zhihao Du, Changfeng Gao, Zhifu Gao, Yue Gu, Ting He, Hangrui Hu, Kai Hu, et al. 2024. Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:2407.04051. — [arXiv:2407.04051](https://arxiv.org/abs/2407.04051) [find](https://scholar.google.com/scholar?q=Keyu+An%2C+Qian+Chen%2C+Chong+Deng%2C+Zhihao+Du%2C+Changfeng+Gao%2C+Zhifu+Gao%2C+Yue+Gu%2C+Ting+He%2C+Hangrui+Hu%2C+Kai+Hu%2C+et+al%2E+2024%2E+Funaudiollm%3A+Voice+understanding+and+generation+foundation+models+for+natural+int)
3. Anonymous. 2025. CLSR: End-to-end contrastive language-speech retriever for better speech retrieval augmented generation. In Submitted to ACL Rolling Review - December 2024. Under review. [find](https://scholar.google.com/scholar?q=Anonymous%2E+2025%2E+CLSR%3A+End%2Dto%2Dend+contrastive+language%2Dspeech+retriever+for+better+speech+retrieval+augmented+generation%2E+In+Submitted+to+ACL+Rolling+Review+%2D+December+2024%2E+Under+review%2E)
4. Rosana Ardila, Megan Branson, Kelly Davis, Michael Kohler, Josh Meyer, Michael Henretty, Reuben Morais, Lindsay Saunders, Francis Tyers, and Gregor Weber. 2020. [Common voice: A massively-multilingual speech corpus](https://md.research.elamur.ai/free/en/papers/ardila-2019-common-voice-massively-multilingual-speech/). In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 421…
5. Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. [Llm2vec: Large language models are secretly powerful text encoders](https://md.research.elamur.ai/free/en/papers/behnamghader-2024-llm2vec-large-language-models-secretly/). Preprint, arXiv:2404.05961.
6. Ciprian Chelba, Timothy J. Hazen, and Murat Saraclar. 2008. Retrieval and browsing of spoken content. IEEE Signal Processing Magazine, 25(3):39–49. [find](https://scholar.google.com/scholar?q=Ciprian+Chelba%2C+Timothy+J%2E+Hazen%2C+and+Murat+Saraclar%2E+2008%2E+Retrieval+and+browsing+of+spoken+content%2E+IEEE+Signal+Processing+Magazine%2C+25%283%29%3A39%E2%80%9349%2E)
7. Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, and William W. Cohen. 2022. [Murag: Multimodal retrieval-augmented generator for open question answering over images and text](https://md.research.elamur.ai/free/en/papers/chen-2022-murag-multimodal-retrieval-augmented-generator/). Preprint, arXiv:2210.02928.
8. Xinyun Chen, Renat Aksitov, Uri Alon, Jie Ren, Kefan Xiao, Pengcheng Yin, Sushant Prakash, Charles Sutton, Xuezhi Wang, and Denny Zhou. 2023. [Universal self-consistency for large language model generation](https://md.research.elamur.ai/free/en/papers/chen-2023-universal-self-consistency-large-language/). arXiv preprint arXiv:2311.17311.
9. Konstantinos Drossos, Samuel Lipping, and Tuomas Virtanen. 2019. Clotho: An audio captioning dataset. Preprint, arXiv:1910.09387. — [arXiv:1910.09387](https://arxiv.org/abs/1910.09387) [find](https://scholar.google.com/scholar?q=Konstantinos+Drossos%2C+Samuel+Lipping%2C+and+Tuomas+Virtanen%2E+2019%2E+Clotho%3A+An+audio+captioning+dataset%2E+Preprint%2C+arXiv%3A1910%2E09387%2E+%E2%80%94+%5BarXiv%3A1910%2E09387%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1910%2E09387%29)
10. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, Fan Yu, Huadai Liu, Zhengyan Sheng, Yue Gu, Chong Deng, Wen Wang, Shiliang Zhang, Zhijie Yan, and Jingren Zhou. 2024. Cosyvoice 2: Scalable streaming speech synthesis with large langua… [find](https://scholar.google.com/scholar?q=Zhihao+Du%2C+Yuxuan+Wang%2C+Qian+Chen%2C+Xian+Shi%2C+Xiang+Lv%2C+Tianyu+Zhao%2C+Zhifu+Gao%2C+Yexin+Yang%2C+Changfeng+Gao%2C+Hui+Wang%2C+Fan+Yu%2C+Huadai+Liu%2C+Zhengyan+Sheng%2C+Yue+Gu%2C+Chong+Deng%2C+Wen+Wang%2C+Shiliang+Zhang%2C+Zh)
11. Benjamin Elizalde, Soham Deshmukh, Mahmoud Al Ismail, and Huaming Wang. 2022. Clap: Learning audio concepts from natural language supervision. Preprint, arXiv:2206.04769. [find](https://scholar.google.com/scholar?q=Benjamin+Elizalde%2C+Soham+Deshmukh%2C+Mahmoud+Al+Ismail%2C+and+Huaming+Wang%2E+2022%2E+Clap%3A+Learning+audio+concepts+from+natural+language+supervision%2E+Preprint%2C+arXiv%3A2206%2E04769%2E)
12. Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, and Michael Auli. 2019. [ELI5: Long form question answering](https://md.research.elamur.ai/free/en/papers/fan-2019-eli5-long-form-question-answering/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3558–3567, Florence, Italy. Association for Computational Linguistics.
13. Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, and Yang Feng. 2024. Llama-omni: Seamless speech interaction with large language models. Preprint, arXiv:2409.06666. [find](https://scholar.google.com/scholar?q=Qingkai+Fang%2C+Shoutao+Guo%2C+Yan+Zhou%2C+Zhengrui+Ma%2C+Shaolei+Zhang%2C+and+Yang+Feng%2E+2024%2E+Llama%2Domni%3A+Seamless+speech+interaction+with+large+language+models%2E+Preprint%2C+arXiv%3A2409%2E06666%2E)
14. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997.
15. Robie Gonzales and Frank Rudzicz. 2024. A retrieval augmented approach for text-to-music generation. In Proceedings of the 3rd Workshop on NLP for Music and Audio (NLP4MusA), pages 31–36, Oakland, USA. Association for Computational Lingustics. [find](https://scholar.google.com/scholar?q=Robie+Gonzales+and+Frank+Rudzicz%2E+2024%2E+A+retrieval+augmented+approach+for+text%2Dto%2Dmusic+generation%2E+In+Proceedings+of+the+3rd+Workshop+on+NLP+for+Music+and+Audio+%28NLP4MusA%29%2C+pages+31%E2%80%9336%2C+Oakland%2C+USA)
16. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. [Realm: Retrieval-augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). Preprint, arXiv:2002.08909.
17. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). Preprint, arXiv:2106.09685.
18. Rongjie Huang, Jiawei Huang, Dongchao Yang, Yi Ren, Luping Liu, Mingze Li, Zhenhui Ye, Jinglin Liu, Xiang Yin, and Zhou Zhao. 2023. Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models. Preprint, arXiv:2301.12661. — [arXiv:2301.12661](https://arxiv.org/abs/2301.12661) [find](https://scholar.google.com/scholar?q=Rongjie+Huang%2C+Jiawei+Huang%2C+Dongchao+Yang%2C+Yi+Ren%2C+Luping+Liu%2C+Mingze+Li%2C+Zhenhui+Ye%2C+Jinglin+Liu%2C+Xiang+Yin%2C+and+Zhou+Zhao%2E+2023%2E+Make%2Dan%2Daudio%3A+Text%2Dto%2Daudio+generation+with+prompt%2Denhanced+diffusi)
19. Shengpeng Ji, Yifu Chen, Minghui Fang, Jialong Zuo, Jingyu Lu, Hanting Wang, Ziyue Jiang, Long Zhou, Shujie Liu, Xize Cheng, Xiaoda Yang, Zehan Wang, Qian Yang, Jian Li, Yidi Jiang, Jingzhen He, Yunfei Chu, Jin Xu, and Zhou Zhao. 2024a. Wavchat: A survey of spoken dialogue models. Preprint, arXiv:24… [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Yifu+Chen%2C+Minghui+Fang%2C+Jialong+Zuo%2C+Jingyu+Lu%2C+Hanting+Wang%2C+Ziyue+Jiang%2C+Long+Zhou%2C+Shujie+Liu%2C+Xize+Cheng%2C+Xiaoda+Yang%2C+Zehan+Wang%2C+Qian+Yang%2C+Jian+Li%2C+Yidi+Jiang%2C+Jingzhen+He%2C+Yunfe)
20. Shengpeng Ji, Ziyue Jiang, Wen Wang, Yifu Chen, Minghui Fang, Jialong Zuo, Qian Yang, Xize Cheng, Zehan Wang, Ruiqi Li, et al. 2024b. Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling. arXiv preprint arXiv:2408.16532. — [arXiv:2408.16532](https://arxiv.org/abs/2408.16532) [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Ziyue+Jiang%2C+Wen+Wang%2C+Yifu+Chen%2C+Minghui+Fang%2C+Jialong+Zuo%2C+Qian+Yang%2C+Xize+Cheng%2C+Zehan+Wang%2C+Ruiqi+Li%2C+et+al%2E+2024b%2E+Wavtokenizer%3A+an+efficient+acoustic+discrete+codec+tokenizer+for+a)
21. Shengpeng Ji, Jialong Zuo, Minghui Fang, Ziyue Jiang, Feiyang Chen, Xinyu Duan, Baoxing Huai, and Zhou Zhao. 2024c. Textrolspeech: A text style control speech corpus with codec language text-to-speech models. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processin… [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Jialong+Zuo%2C+Minghui+Fang%2C+Ziyue+Jiang%2C+Feiyang+Chen%2C+Xinyu+Duan%2C+Baoxing+Huai%2C+and+Zhou+Zhao%2E+2024c%2E+Textrolspeech%3A+A+text+style+control+speech+corpus+with+codec+language+text%2Dto%2Dspeech)
22. Shengpeng Ji, Jialong Zuo, Wen Wang, Minghui Fang, Siqi Zheng, Qian Chen, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, et al. 2024d. Controlspeech: Towards simultaneous zero-shot speaker cloning and zero-shot language style control with decoupled codec. arXiv preprint arXiv:2406.01205. — [arXiv:2406.01205](https://arxiv.org/abs/2406.01205) [find](https://scholar.google.com/scholar?q=Shengpeng+Ji%2C+Jialong+Zuo%2C+Wen+Wang%2C+Minghui+Fang%2C+Siqi+Zheng%2C+Qian+Chen%2C+Ziyue+Jiang%2C+Hai+Huang%2C+Zehan+Wang%2C+Xize+Cheng%2C+et+al%2E+2024d%2E+Controlspeech%3A+Towards+simultaneous+zero%2Dshot+speaker+cloning+an)
23. Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, and Fuzhen Zhuang. 2023. [Scaling sentence embeddings with large language models](https://md.research.elamur.ai/free/en/papers/jiang-2024-scaling-sentence-embeddings-large-language/). Preprint, arXiv:2307.16645.
24. Ting Jiang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, and Fuzhen Zhuang. 2024. E5-v: Universal embeddings with multimodal large language models. Preprint, arXiv:2407.12580. — [arXiv:2407.12580](https://arxiv.org/abs/2407.12580) [find](https://scholar.google.com/scholar?q=Ting+Jiang%2C+Minghui+Song%2C+Zihan+Zhang%2C+Haizhen+Huang%2C+Weiwei+Deng%2C+Feng+Sun%2C+Qi+Zhang%2C+Deqing+Wang%2C+and+Fuzhen+Zhuang%2E+2024%2E+E5%2Dv%3A+Universal+embeddings+with+multimodal+large+language+models%2E+Preprint%2C)
25. Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2025. Vlm2vec: Training vision-language models for massive multimodal embedding tasks. Preprint, arXiv:2410.05160. — [arXiv:2410.05160](https://arxiv.org/abs/2410.05160) [find](https://scholar.google.com/scholar?q=Ziyan+Jiang%2C+Rui+Meng%2C+Xinyi+Yang%2C+Semih+Yavuz%2C+Yingbo+Zhou%2C+and+Wenhu+Chen%2E+2025%2E+Vlm2vec%3A+Training+vision%2Dlanguage+models+for+massive+multimodal+embedding+tasks%2E+Preprint%2C+arXiv%3A2410%2E05160%2E+%E2%80%94+%5BarXiv)
26. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. [TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver…
27. Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. [AudioCaps: Generating captions for audios in the wild](https://md.research.elamur.ai/free/en/papers/kim-2019-audiocaps-generating-captions-audios-wild/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Pa…
28. Yuma Koizumi, Yasunori Ohishi, Daisuke Niizumi, Daiki Takeuchi, and Masahiro Yasuda. 2020. Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval. Preprint, arXiv:2012.07331. — [arXiv:2012.07331](https://arxiv.org/abs/2012.07331) [find](https://scholar.google.com/scholar?q=Yuma+Koizumi%2C+Yasunori+Ohishi%2C+Daisuke+Niizumi%2C+Daiki+Takeuchi%2C+and+Masahiro+Yasuda%2E+2020%2E+Audio+captioning+using+pre%2Dtrained+large%2Dscale+language+model+guided+by+audio%2Dbased+similar+caption+retrieval)
29. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35:22199– 22213.
30. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/)
31. Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2025. [Nv-embed: Improved techniques for training llms as generalist embedding models](https://md.research.elamur.ai/free/en/papers/lee-2024-nv-embed-improved-techniques-training/). Preprint, arXiv:2405.17428.
32. Lin-shan Lee, James Glass, Hung-yi Lee, and Chunan Chan. 2015. Spoken content retrieval—beyond cascading speech recognition with text retrieval. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23(9):1389–1420. [find](https://scholar.google.com/scholar?q=Lin%2Dshan+Lee%2C+James+Glass%2C+Hung%2Dyi+Lee%2C+and+Chunan+Chan%2E+2015%2E+Spoken+content+retrieval%E2%80%94beyond+cascading+speech+recognition+with+text+retrieval%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Language+Pr)
33. Chaofan Li, MingHao Qin, Shitao Xiao, Jianlyu Chen, Kun Luo, Yingxia Shao, Defu Lian, and Zheng Liu. 2024. Making text embedders few-shot learners. Preprint, arXiv:2409.15700. [find](https://scholar.google.com/scholar?q=Chaofan+Li%2C+MingHao+Qin%2C+Shitao+Xiao%2C+Jianlyu+Chen%2C+Kun+Luo%2C+Yingxia+Shao%2C+Defu+Lian%2C+and+Zheng+Liu%2E+2024%2E+Making+text+embedders+few%2Dshot+learners%2E+Preprint%2C+arXiv%3A2409%2E15700%2E)
34. Chia-Hsuan Li, Szu-Lin Wu, Chi-Liang Liu, and Hung yi Lee. 2018. Spoken squad: A study of mitigating the impact of speech recognition errors on listening comprehension. Preprint, arXiv:1804.00320. — [arXiv:1804.00320](https://arxiv.org/abs/1804.00320) [find](https://scholar.google.com/scholar?q=Chia%2DHsuan+Li%2C+Szu%2DLin+Wu%2C+Chi%2DLiang+Liu%2C+and+Hung+yi+Lee%2E+2018%2E+Spoken+squad%3A+A+study+of+mitigating+the+impact+of+speech+recognition+errors+on+listening+comprehension%2E+Preprint%2C+arXiv%3A1804%2E00320%2E+%E2%80%94+%5B)
35. Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, and Ge Yu. 2023. Universal vision-language dense retrieval: Learning a unified representation space for multi-modal retrieval. Preprint, arXiv:2209.00179. — [arXiv:2209.00179](https://arxiv.org/abs/2209.00179) [find](https://scholar.google.com/scholar?q=Zhenghao+Liu%2C+Chenyan+Xiong%2C+Yuanhuiyi+Lv%2C+Zhiyuan+Liu%2C+and+Ge+Yu%2E+2023%2E+Universal+vision%2Dlanguage+dense+retrieval%3A+Learning+a+unified+representation+space+for+multi%2Dmodal+retrieval%2E+Preprint%2C+arXiv%3A2)
36. Do June Min, Karel Mundnich, Andy Lapastora, Erfan Soltanmohammadi, Srikanth Ronanki, and Kyu Han. 2025. Speech retrieval-augmented generation without automatic speech recognition. Preprint, arXiv:2412.16500. — [arXiv:2412.16500](https://arxiv.org/abs/2412.16500) [find](https://scholar.google.com/scholar?q=Do+June+Min%2C+Karel+Mundnich%2C+Andy+Lapastora%2C+Erfan+Soltanmohammadi%2C+Srikanth+Ronanki%2C+and+Kyu+Han%2E+2025%2E+Speech+retrieval%2Daugmented+generation+without+automatic+speech+recognition%2E+Preprint%2C+arXiv%3A241)
37. Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. Voxceleb: A large-scale speaker identification dataset. In Interspeech 2017, interspeech_2017. ISCA. [find](https://scholar.google.com/scholar?q=Arsha+Nagrani%2C+Joon+Son+Chung%2C+and+Andrew+Zisserman%2E+2017%2E+Voxceleb%3A+A+large%2Dscale+speaker+identification+dataset%2E+In+Interspeech+2017%2C+interspeech%5F2017%2E+ISCA%2E)
38. Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, and Siliang Tang. 2024. [Graph retrieval-augmented generation: A survey](https://md.research.elamur.ai/free/en/papers/peng-2024-graph-retrieval-augmented-generation-survey/). Preprint, arXiv:2408.08921.
39. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [Squad: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). Preprint, arXiv:1606.05250.
40. Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin, Ankita Pasad, Felix Wu, Roshan Sharma, Wei-Lun Wu, Hung-yi Lee, Karen Livescu, and Shinji Watanabe. 2023. SLUE phase-2: A benchmark suite of diverse spoken language understanding tasks. In Proceedings of the 61st Annual Meeting of the Association for Compu… [find](https://scholar.google.com/scholar?q=Suwon+Shon%2C+Siddhant+Arora%2C+Chyi%2DJiunn+Lin%2C+Ankita+Pasad%2C+Felix+Wu%2C+Roshan+Sharma%2C+Wei%2DLun+Wu%2C+Hung%2Dyi+Lee%2C+Karen+Livescu%2C+and+Shinji+Watanabe%2E+2023%2E+SLUE+phase%2D2%3A+A+benchmark+suite+of+diverse+spoken+)
41. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). Preprint…
42. Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2019. [Representation learning with contrastive predictive coding](https://md.research.elamur.ai/free/en/papers/oord-2018-representation-learning-contrastive-predictive-coding/). Preprint, arXiv:1807.03748.
43. Zhiguo Wang, Wael Hamza, and Radu Florian. 2017. [Bilateral multi-perspective matching for natural language sentences](https://md.research.elamur.ai/free/en/papers/wang-2017-bilateral-multi-perspective-matching-natural/). Preprint, arXiv:1702.03814.
44. Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2023. Uniir: Training and benchmarking universal multimodal information retrievers. Preprint, arXiv:2311.17136. — [arXiv:2311.17136](https://arxiv.org/abs/2311.17136) [find](https://scholar.google.com/scholar?q=Cong+Wei%2C+Yang+Chen%2C+Haonan+Chen%2C+Hexiang+Hu%2C+Ge+Zhang%2C+Jie+Fu%2C+Alan+Ritter%2C+and+Wenhu+Chen%2E+2023%2E+Uniir%3A+Training+and+benchmarking+universal+multimodal+information+retrievers%2E+Preprint%2C+arXiv%3A2311%2E17)
45. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). Preprint, arXiv:1809.09600.
46. Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2024. Gme: Improving universal multimodal retrieval by multimodal llms. Preprint, arXiv:2412.16855. — [arXiv:2412.16855](https://arxiv.org/abs/2412.16855) [find](https://scholar.google.com/scholar?q=Xin+Zhang%2C+Yanzhao+Zhang%2C+Wen+Xie%2C+Mingxin+Li%2C+Ziqi+Dai%2C+Dingkun+Long%2C+Pengjun+Xie%2C+Meishan+Zhang%2C+Wenjie+Li%2C+and+Min+Zhang%2E+2024%2E+Gme%3A+Improving+universal+multimodal+retrieval+by+multimodal+llms%2E+Pre)
47. Jinming Zhao, Gholamreza Haffari, and Ehsan Shareghi. 2023. Generating synthetic speech from SpokenVo-cab for speech translation. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1975–1981, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jinming+Zhao%2C+Gholamreza+Haffari%2C+and+Ehsan+Shareghi%2E+2023%2E+Generating+synthetic+speech+from+SpokenVo%2Dcab+for+speech+translation%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EACL+202)

*Updated 30 October 2026*