Elamur Research⌕
☰
home / papers / 2026 / SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

Paper · 2026 · Jingyu Lu, Yuhan Wang, Fan Zhuo et al.

Summary

End-to-end spoken dialogue systems need reward signals that go beyond text semantics. The authors identify two weaknesses in current evaluators. The first is a modality gap: prosody, emotion and channel cues are invisible to text-based judges. The second is a colloquialness gap: written-style replies sound scripted when spoken.

To address both, they built SDiaReward-Dataset, a corpus of episode-level preference pairs of two kinds:

  • Modality pairs contrast real human dialogue audio with dialogue-consistent synthetic speech.
  • Colloquialness pairs contrast written-style dialogues with spoken-style rewrites.

On this data they trained SDiaReward, a reward model that takes whole multi-turn speech episodes as input and learns from pairwise preferences. It scores both aspects within a single evaluator. They also released ESDR-Bench, a stratified benchmark with multidimensional annotations for episode-level evaluation.

SDiaReward reaches state-of-the-art pairwise preference accuracy and clearly beats general-purpose audio LLMs, which often cannot tell natural speech from synthesis. Analysis suggests the model ranks pairs by relative expressiveness within each acoustic domain rather than by detecting synthesis artifacts. This makes it a promising foundation for future speech alignment methods such as DPO or GRPO.

Key points

  • Corpus size: SDiaReward-Dataset contains 13,356 dialogue pairs, split into 11,630 for training and 1,726 for validation. The training portion covers about 11k pairs, or roughly 200 hours of paired speech.
  • Modality pairs by source:
    • Wild YouTube conversations: 7,703 pairs.
    • Semi-wild acted dialogues from MELD: 495 pairs.
    • Scripted studio recordings from DailyTalk: 2,658 pairs.
    • All negatives were synthesized with the SoulX-Podcast Dialogue-TTS system to serve as hard negatives.
  • Colloquialness pairs: 2,500 pairs built from 250 scenarios across 10 domains. LLMs generated written-style dialogues, which were then rewritten in spoken style under the same acoustic conditions.
  • Audio pipeline: web audio passed through speech enhancement, neural speaker diarization, and VAD/ASR-aligned segmentation. Segments were then grouped into continuous multi-turn episodes. Episodes carry emotion, sentiment and dialogue-act metadata used to stratify ESDR-Bench.
  • Release: only derived artifacts (metadata, preference labels, splits, evaluation scripts) are released, for non-commercial research. Raw audio and speaker identifiers are excluded. The authors report that absolute reward scores vary by domain, with Scripted data scoring lower than Wild.

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

🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

Cite

Cite as Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang and Zhou Zhao. 2026. SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness. Proceedings of the 64th 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. DOI 10.18653/v1/2026.acl-long.185

@inproceedings{lu2026sdiareward,
  title = {{SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness}},
  author = {Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang and Zhou Zhao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.185},
  url = {https://doi.org/10.18653/v1/2026.acl-long.185}
}

References

61 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ralph Allan Bradley and Milton E. Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324– 345. find
  2. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, and 1 others. 2024. Internlm2 technical report. arXiv preprint arXiv:2403.17297.
  3. Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, and Zhou Zhao. 2026a. Wavalign: Enhancing intelligence and expressiveness in spoken dialogue models via adaptive hybrid post-training. Preprint, arXiv:2604.14932. find
  4. Yifu Chen, Shengpeng Ji, Zhengqing Liu, Qian Chen, Wen Wang, Ziqing Wang, Yangzhuo Li, Tianle Liang, and Zhou Zhao. 2026b. Dual-axis generative reward model toward semantic and turn-taking robustness in interactive spoken dialogue models. Preprint, arXiv:2604.14920.
  5. 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. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  6. Yuan Ge, Junxiang Zhang, Xiaoqian Liu, Bei Li, Xiangnan Ma, Chenglong Wang, Kaiyang Ye, Yangfan Du, Linfeng Zhang, Yuxin Huang, and 1 others. 2026. Sagelm: A multi-aspect and explainable large language model for speech judgement. In Proceedings of the AAAI Conference on Artificial Intelligence, volu… find
  7. Yiming Chen, Xianghu Yue, Chen Zhang, Xiaoxue Gao, Robby T Tan, and Haizhou Li. 2024. Voicebench: Benchmarking llm-based voice assistants. arXiv preprint arXiv:2410.17196.
  8. Gustking. 2024. wav2vec2-large-xlsr-deepfake-audio-classification. https://huggingface.co/Gustking/ wav2vec2-large-xlsr-deepfake-audio-classification. ↗
  9. Xize Cheng, Dongjie Fu, Xiaoda Yang, Minghui Fang, Ruofan Hu, Jingyu Lu, Bai Jionghao, Zehan Wang, Shengpeng Ji, Rongjie Huang, and 1 others. 2025a. Omnichat: Enhancing spoken dialogue systems with scalable synthetic data for diverse scenarios. arXiv preprint arXiv:2501.01384. — [arXiv:2501.01384](https://arxiv.org/abs/2501.01384) find
  10. Haorui He, Zengqiang Shang, Chaoren Wang, Xuyuan Li, Yicheng Gu, Hua Hua, Liwei Liu, Chen Yang, Jiaqi Li, Peiyang Shi, and 1 others. 2024. Emilia: An extensive, multilingual, and diverse speech dataset for large-scale speech generation. In 2024 IEEE Spoken Language Technology Workshop (SLT), pages 8… find
  11. Xize Cheng, Ruofan Hu, Xiaoda Yang, Jingyu Lu, Dongjie Fu, Zehan Wang, Shengpeng Ji, Rongjie Huang, Boyang Zhang, Tao Jin, and 1 others. 2025b. Voxdialogue: Can spoken dialogue systems understand information beyond words? In The Thirteenth International Conference on Learning Representations. find
  12. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  13. Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30. find
  14. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  15. Alexandre Défossez, Laurent Mazaré, Manu Orsini, Amélie Royer, Patrick Pérez, Hervé Jégou, Edouard Grave, and Neil Zeghidour. 2024. Moshi: a speech-text foundation model for real-time dialogue. arXiv preprint arXiv:2410.00037.
  16. Ding Ding, Zeqian Ju, Yichong Leng, Songxiang Liu, Tong Liu, Zeyu Shang, Kai Shen, Wei Song, Xu Tan, Heyi Tang, and 1 others. 2025. Kimi-audio technical report. arXiv preprint arXiv:2504.18425.
  17. Shengpeng Ji, Yifu Chen, Minghui Fang, Jialong Zuo, Jingyu Lu, Hanting Wang, Ziyue Jiang, Long Zhou, Shujie Liu, Xize Cheng, and 1 others. 2024a. Wavchat: A survey of spoken dialogue models. arXiv preprint arXiv:2411.13577. find
  18. Shengpeng Ji, Ziyue Jiang, Wen Wang, Yifu Chen, Minghui Fang, Jialong Zuo, Qian Yang, Xize Cheng, Zehan Wang, Ruiqi Li, and 1 others. 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
  19. Shengpeng Ji, Tianle Liang, Yangzhuo Li, Jialong Zuo, Minghui Fang, Jinzheng He, Yifu Chen, Zhengqing Liu, Ziyue Jiang, Xize Cheng, and 1 others. 2025. Wavreward: Spoken dialogue models with generalist reward evaluators. arXiv preprint arXiv:2505.09558. — [arXiv:2505.09558](https://arxiv.org/abs/2505.09558) find
  20. XU Ji, PAN Jielin, and YAN Yonghong. 2016. Agglutinative language speech recognition using automatic allophone deriving. Chinese Journal of Electronics, 25(2):328–333. find
  21. Zhihao Du, Yuxuan Wang, Qian Chen, Xian Shi, Xiang Lv, Tianyu Zhao, Zhifu Gao, Yexin Yang, Changfeng Gao, Hui Wang, and 1 others. 2024. Cosyvoice 2: Scalable streaming speech synthesis with large language models. arXiv preprint arXiv:2412.10117. find
  22. Dongfu Jiang, Xiang Ren, and Bill Yuchen Lin. 2023. LLM-blender: Ensembling large language models with pairwise ranking and generative fusion. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14165–14178, Toronto, Canada. Assoc…
  23. Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D’Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, and 1 others. 2023. Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking. arXiv preprint arXiv:2312.09244. — [arXiv:2312.09244](https://arxiv.org/abs/2312.09244) find
  24. Nathan Lambert, Valentina Pyatkin, Jacob Morrison, Lester James Validad Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, and 1 others. 2025. Rewardbench: Evaluating reward models for language modeling. In Findings of the Association for Computational Linguis… find
  25. Keon Lee, Kyumin Park, and Daeyoung Kim. 2023. Dailytalk: Spoken dialogue dataset for conversational text-to-speech. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. find
  26. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, 36:53728–53741.
  27. Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haorong Ying, Yule Wang, Junbo Li, Jun Fang, and Zhou Zhao. 2026. Wavbench: Benchmarking reasoning, colloquialism, and paralinguistics for end-to-end spoken dialogue models. arXiv preprint arXiv:2602.12135. — [arXiv:2602.12135](https://arxiv.org/abs/2602.12135) find
  28. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805.
  29. Yantao Liu, Zijun Yao, Rui Min, Yixin Cao, Lei Hou, and Juanzi Li. 2024. Rm-bench: Benchmarking reward models of language models with subtlety and style. arXiv preprint arXiv:2410.16184.
  30. Silero Team. 2024. Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier. https://github.com/ snakers4/silero-vad. ↗
  31. Zuwei Long, Yunhang Shen, Chaoyou Fu, Heting Gao, Lijiang Li, Peixian Chen, Mengdan Zhang, Hang Shao, Jian Li, Jinlong Peng, and 1 others. 2025. Vita-audio: Fast interleaved cross-modal token generation for efficient large speech-language model. arXiv preprint arXiv:2505.03739. — [arXiv:2505.03739](https://arxiv.org/abs/2505.03739) find
  32. OpenAI. 2024. Gpt-4.1 mini. https://platform. Ac-openai.com/docs/models/gpt-4.1-mini. cessed: 2026-01-06. find
  33. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744.
  34. Changhao Pan, Dongyu Yao, Yu Zhang, Wenxiang Guo, Jingyu Lu, Zhiyuan Zhu, and Zhou Zhao. 2025. Synthetic singers: A review of deep-learning-based singing voice synthesis approaches. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the… find
  35. Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2019. Meld: A multimodal multi-party dataset for emotion recognition in conversations. In Proceedings of the 57th annual meeting of the association for computational linguistics, pages 527–536.
  36. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  37. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust speech recognition via large-scale weak supervision. arXiv preprint.
  38. Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallouédec. 2020. Trl: Transformer reinforcement learning. https://github.com/huggingface/trl. ↗
  39. Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. 2025. Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236. — [arXiv:2503.05236](https://arxiv.org/abs/2503.05236) find
  40. Lian Wenjuan, Zhang Chengxin, Zhang Hongbao, Jia Bin, and Liu Baihang. 2025. Rulemaster+: Llm-based automated rule generation framework for intrusion detection systems. Chinese Journal of Electronics, 34(5):1402–1415. xAI. 2025. Grok 4.1. https://x.ai/news/grok-4-1. Accessed: 2026-01-06. ↗
  41. Hanke Xie, Haopeng Lin, Wenxiao Cao, Dake Guo, Wenjie Tian, Jun Wu, Hanlin Wen, Ruixuan Shang, Hongmei Liu, Zhiqi Jiang, and 1 others. 2025a. Soulx-podcast: Towards realistic long-form podcasts with dialectal and paralinguistic diversity. arXiv preprint arXiv:2510.23541. — [arXiv:2510.23541](https://arxiv.org/abs/2510.23541) find
  42. Kun Xie, Feiyu Shen, Junjie Li, Fenglong Xie, Xu Tang, and Yao Hu. 2025b. Fireredtts-2: Towards long conversational speech generation for podcast and chatbot. arXiv preprint arXiv:2509.02020. — [arXiv:2509.02020](https://arxiv.org/abs/2509.02020) find
  43. Zhifei Xie, Mingbao Lin, Zihang Liu, Pengcheng Wu, Shuicheng Yan, and Chunyan Miao. 2025c. Audio-reasoner: Improving reasoning capability in large audio language models. arXiv preprint arXiv:2503.02318.
  44. Zhifei Xie and Changqiao Wu. 2024. Mini-omni: Language models can hear, talk while thinking in streaming. arXiv preprint arXiv:2408.16725. find
  45. Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, 36:15903– 15935. find
  46. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, and 1 others. 2025a. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — Qwen2.5-Omni Technical Report
  47. SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 15757–15773, Singapore. Association for Computational Linguistics.
  48. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, and 19 others. 2025b. Qwen3-omni technical report. Preprint, arXiv:2509.17765.
  49. Xueyao Zhang, Chaoren Wang, Huan Liao, Ziniu Li, Yuancheng Wang, Li Wang, Dongya Jia, Yuanzhe Chen, Xiulin Li, Zhuo Chen, and 1 others. 2025. Speechjudge: Towards human-level judgment for speech naturalness. arXiv preprint arXiv:2511.07931. — [arXiv:2511.07931](https://arxiv.org/abs/2511.07931) find
  50. Ruiqi Yan, Xiquan Li, Wenxi Chen, Zhikang Niu, Chen Yang, Ziyang Ma, Kai Yu, and Xie Chen. 2025. URO-bench: Towards comprehensive evaluation for end-to-end spoken dialogue models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17211–17242, Suzhou, China. Association… find
  51. Yu Zhang, Changhao Pan, Wenxiang Guo, Ruiqi Li, Zhiyuan Zhu, Jialei Wang, Wenhao Xu, Jingyu Lu, Zhiqing Hong, Chuxin Wang, and 1 others. 2024. Gtsinger: A global multi-technique singing corpus with realistic music scores for all singing tasks. Advances in Neural Information Processing Systems, 37:11… find
  52. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  53. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, and 1 others. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223, 1(2).
  54. Shu-wen Yang, Ming Tu, Andy T Liu, Xinghua Qu, Hung-yi Lee, Lu Lu, Yuxuan Wang, and Yonghui Wu. 2025b. Paras2s: Benchmarking and aligning spoken language models for paralinguistic-aware speech-to-speech interaction. arXiv preprint arXiv:2511.08723. — [arXiv:2511.08723](https://arxiv.org/abs/2511.08723) find
  55. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems, 36:46595–46623.
  56. Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, and 1 others. 2024a. Audiovsr: Enhancing video speech recognition with audio data. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Proc… find
  57. Xiaoda Yang, Xize Cheng, Dongjie Fu, Minghui Fang, Jialung Zuo, Shengpeng Ji, Zhou Zhao, and Jin Tao. 2024b. Synctalklip: Highly synchronized lip-readable speaker generation with multi-task learning. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 8149–8158. find
  58. Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and 1 others. 2024. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In Proceedings of the IEEE/CVF Conference on Computer Vis… find
  59. Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, and 1 others. 2025. Internlm-xcomposer2. 5-reward: A simple yet effective multi-modal reward model. arXiv preprint arXiv:2501.12368. find
  60. Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, and Xipeng Qiu. 2023. find
  61. Jialun Zhong, Wei Shen, Yanzeng Li, Songyang Gao, Hua Lu, Yicheng Chen, Yang Zhang, Wei Zhou, Jinjie Gu, and Lei Zou. 2025. A comprehensive survey of reward models: Taxonomy, applications, challenges, and future. arXiv preprint arXiv:2504.12328. — [arXiv:2504.12328](https://arxiv.org/abs/2504.12328) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lu-2026-sdiareward-modeling-benchmarking-spoken-dialogue/