ReAct: Synergizing Reasoning and Acting in Language Models (2022 · 2,591 citations)
Large language models have mostly been studied either as reasoners, which produce chain-of-thought explanations, or as actors, which produce plans and commands for an environment.
SLM: Bridge the thin gap between speech and text foundation models (2023 · 54 citations)
Building speech-language systems usually demands large amounts of paired audio-text data or costly end-to-end training.

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Tree of Thoughts: Deliberate Problem Solving with Large Language Models ↗arXiv:2305.10601 · no summary yetShunyu Yao et al.2023 · 2,671 citations
ReAct: Synergizing Reasoning and Acting in Language ModelsarXiv:2210.03629Shunyu Yao, Jeffrey Zhao, Dian Yu, et al.2022 · 2,591 citations
Accent detection and speech recognition for Shanghai-accented Mandarin ↗Interspeech (USB) · no summary yetYanli Zheng et al.2005 · 93 citations
Extracting Symptoms and their Status from Clinical Conversations ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetNan Du et al.2019 · 81 citations
SLM: Bridge the thin gap between speech and text foundation modelsIEEE Automatic Speech Recognition and Understanding Workshop (ASRU)Mingqiu Wang, Wei Han, Izhak Shafran, et al.2023 · 54 citations

Co-authors here

9 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU): ASRU 2023
Interspeech (USB)
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Papers of our library cite their works 5,928 times (of the 149,439 papers whose bibliographies we read); 1,082 citing papers with a page here →.

Updated 1 November 2026