--- title: "Zhoujun Li — author profile and papers" description: "Zhoujun Li, China Telecom (China): 2 papers on Elamur Research (2017–2023), h-index 51 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/zhoujun-li/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhoujun-li/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhoujun Li # Zhoujun Li Zhoujun Li works in natural language processing. The papers here cover [dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) and the testing of large language models that call external tools. Both share a question: how a system should choose a reply or an action when it has a rich context to weigh. In one paper that means the reply that suits a whole conversation. In the other it means the API to invoke, and when to invoke it. The work draws on retrieval-style matching and on executable benchmarks, and it touches information retrieval, language models and [evaluation and benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/). The most cited paper here is [Sequential Matching Network](https://md.research.elamur.ai/free/en/papers/wu-2017-sequential-matching-network-new-architecture/) (2017). It addresses multi-turn response selection for retrieval-based chatbots. Earlier models squeezed the conversation into a single vector before comparing it with a candidate reply. This model instead matches the candidate against each utterance, at both the word level and the contextual level. It then feeds these per-turn signals, in order, into a recurrent network, which can learn to give little weight to turns that carry no useful information. The more recent work turns to large language models that use tools. [API-Bank](https://md.research.elamur.ai/free/en/papers/li-2023-api-bank-comprehensive-benchmark-tool/) (2023) starts from a survey of 500 prospective users. From it the authors define three graded skills: calling an API directly, first retrieving and then calling one, and planning, retrieving and calling together. Models are tested in an executable environment against working API implementations. A search tool covers cases where the right APIs are not supplied in advance. Li's bylines are mainly at Beihang University and its State Key Laboratory of Software Development Environment in Beijing, from 2006 onward. China Telecom appears from 2025, and Shenzhen University appears between 2019 and 2023. Co-authors on the papers here include [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/), [Wei Wu](https://md.research.elamur.ai/free/en/authors/wei-wu/), [Yu Wu](https://md.research.elamur.ai/free/en/authors/yu-wu/), [Minghao Li](https://md.research.elamur.ai/free/en/authors/minghao-li/), Yongbin Li, Fei Huang and Bowen Yu. 2 papers on this site · 2017–2023 current affiliation [China Telecom (China)](https://ror.org/03jgnzt20), Changsha, China; [China Telecom](https://ror.org/05p67dv18), Beijing, China; [State Key Laboratory of Software Development Environment](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-software-development-environment/), Beijing; [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/), Beijing, China Zhoujun Li has 2 papers on this site, in 2017–2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Bowen Yu](https://md.research.elamur.ai/free/en/authors/bowen-yu/), [Fei Huang](https://md.research.elamur.ai/free/en/authors/fei-huang/), [Feifan Song](https://md.research.elamur.ai/free/en/authors/feifan-song/). [OpenAlex](https://openalex.org/A5036786337) · [ORCID](https://orcid.org/0000-0002-9603-9713) · [**h-index 51**](https://openalex.org/authors/A5036786337) · [573 works](https://openalex.org/works?filter=author.id:A5036786337) · [9 869 citations](https://openalex.org/works?filter=author.id:A5036786337&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/zhoujun-li/#papers) · [518 citations in our library](https://md.research.elamur.ai/free/en/authors/zhoujun-li/cited-by/) · 11 more works in our library The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Zhoujun+Li) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhoujun+Li) · [dblp](https://dblp.org/search?q=Zhoujun+Li) · [ACL Anthology](https://aclanthology.org/search/?q=Zhoujun+Li) ## Affiliations - [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) · Beijing, China —current · 2006–2026 on 496 papers - [State Key Laboratory of Software Development Environment](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-software-development-environment/) · Beijing —current · 2011–2026 on 193 papers - [China Telecom](https://ror.org/05p67dv18) · Beijing, China —current · 2025–2026 on 2 papers - [China Telecom (China)](https://ror.org/03jgnzt20) · Changsha, China —current · 2025–2026 on 2 papers - [Suzhou University of Science and Technology](https://ror.org/04en8wb91) · Suzhou, China —2023–2025 on 2 papers - [Beijing Information Science & Technology University](https://ror.org/04xnqep60) · Beijing, China —2024 on 2 papers - [Wuhan Huaxia University of Technology](https://ror.org/0529v2183) · Wuhan, China —2024 on 2 papers - [Shenzhen University](https://ror.org/01vy4gh70) · Shenzhen, China —2019–2023 on 11 papers - [Microsoft Research Asia (China)](https://md.research.elamur.ai/free/en/companies/microsoft-research-asia/) · Beijing, China —2021–2023 on 2 papers - [Tencent (China)](https://md.research.elamur.ai/free/en/companies/tencent/) · Shenzhen, China —2021–2022 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 20 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Dialogue systems 1](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Information retrieval & search 1](https://md.research.elamur.ai/free/en/topics/information-retrieval/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/li-2023-api-bank-comprehensive-benchmark-tool/) ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/wu-2017-sequential-matching-network-new-architecture/) ## Papers The most cited first (OpenAlex and our library). 1. **[Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots](https://md.research.elamur.ai/free/en/papers/wu-2017-sequential-matching-network-new-architecture/)** *(2017 · 624 citations)* The paper addresses multi-turn response selection for retrieval-based chatbots: given a conversation history and a pool of candidate replies, the system must pick the reply that fits the whole dialogue, not just the last message. 2. **[API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://md.research.elamur.ai/free/en/papers/li-2023-api-bank-comprehensive-benchmark-tool/)** *(2023 · 281 citations)* LLMs can be extended with external tools, but it has been unclear how well current models actually use APIs, how this skill can be improved, and what still goes wrong. ## Also in our library 11 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 9 co-authors with a page, the most papers together first. - [Bowen Yu](https://md.research.elamur.ai/free/en/authors/bowen-yu/) - [Fei Huang](https://md.research.elamur.ai/free/en/authors/fei-huang/) - [Feifan Song](https://md.research.elamur.ai/free/en/authors/feifan-song/) - [Haiyang Yu](https://md.research.elamur.ai/free/en/authors/haiyang-yu/) - [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/) - [Minghao Li](https://md.research.elamur.ai/free/en/authors/minghao-li/) - [Wei Wu](https://md.research.elamur.ai/free/en/authors/wei-wu/) - [Yongbin Li](https://md.research.elamur.ai/free/en/authors/yongbin-li/) - [Yu Wu](https://md.research.elamur.ai/free/en/authors/yu-wu/) ## Cited by Papers of our library cite their works 518 times (of the 140 884 papers whose bibliographies we read); [19 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhoujun-li/cited-by/).