--- title: "Caiqi Zhang — author profile and papers — Elamur Research" description: "Caiqi Zhang, University of Cambridge: 6 papers on Elamur Research (2024–2026), h-index 5 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/caiqi-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/caiqi-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Caiqi Zhang # Caiqi Zhang Caiqi Zhang has 6 papers in our library, in 2024–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Nigel Collier](https://md.research.elamur.ai/free/en/authors/nigel-collier/), [Xiaochen Zhu](https://md.research.elamur.ai/free/en/authors/xiaochen-zhu/), [Andreas Vlachos](https://md.research.elamur.ai/free/en/authors/andreas-vlachos/). 6 papers in our library · 2024–2026 [OpenAlex](https://openalex.org/A5064109244) · [**h-index 5**](https://openalex.org/authors/A5064109244) · [28 works](https://openalex.org/works?filter=author.id:A5064109244) · [55 citations](https://openalex.org/works?filter=author.id:A5064109244&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 6 works in our library](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/#papers) · [🔗 Cited 65 times in our library](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/cited-by/) · [⭐ Paper Stars ranking: #8200](https://md.research.elamur.ai/free/en/paper-stars/page/82/#star-8200) 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=Caiqi+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Caiqi+Zhang) · [dblp](https://dblp.org/search?q=Caiqi+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Caiqi+Zhang) ## Affiliations [🎓**University of Cambridge** Cambridge · United Kingdom 2023–2026 · 18 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) · [🎓**Hong Kong Polytechnic University** Hong Kong · China 2021–2023 · 3 papers](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) · [🏢**China National Offshore Oil Corporation** Beijing · China 2016–2018 · 2 papers](https://ror.org/054dq0621) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 6 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 6 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 6 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 6 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Physics and Astronomy · 1 work](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/) · [Statistical and Nonlinear Physics · 1 work](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/statistical-and-nonlinear-physics/) 🧭 Topics 1 Research subjects and languages the work is about.[Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2026** 3 papers](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/year/2026/) · [**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/year/2025/) · [**2024** 1 paper](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/year/2024/) ## Papers The most cited first (OpenAlex and our library). 1. **[LUQ: Long-text Uncertainty Quantification for LLMs](https://md.research.elamur.ai/free/en/papers/zhang-2024-luq-long-text-uncertainty-quantification/)** *(2024 · 42 citations)* Most uncertainty quantification (UQ) work for LLMs targets very short answers, usually under ten words, and often needs access to logits. 2. **[Conformity in Large Language Models](https://md.research.elamur.ai/free/en/papers/zhu-2025-conformity-large-language-models/)** *(2025 · 18 citations)* LLMs increasingly serve as conversational partners and as members of multi-agent ensembles. A tendency to side with a majority, even a wrong one, can therefore undermine their usefulness. The authors adapt the classic Asch conformity paradigm to LLMs. In a scripted dialogue, the model answers a question last, after… 3. **[LoGU: Long-form Generation with Uncertainty Expressions](https://md.research.elamur.ai/free/en/papers/yang-2025-logu-long-form-generation-uncertainty/)** *(2025 · 13 citations)* Work on getting LLMs to admit what they do not know has mostly targeted short-form QA, where one confidence signal covers a single answer. 4. **[Confidence Estimation for LLMs in Multi-turn Interactions](https://md.research.elamur.ai/free/en/papers/zhang-2026-confidence-estimation-llms-multi-turn/)** *(2026 · 7 citations)* Most work on LLM confidence estimation looks at single questions answered once. This paper studies a different case: multi-turn dialogue, where useful information arrives over several turns. The authors argue that a good confidence signal in this setting must do two things. It should be calibrated at each turn, and… 5. **[Demystifying Multi-Agent Debate: The Role of Confidence and Diversity](https://md.research.elamur.ai/free/en/papers/zhu-2026-demystifying-multi-agent-debate-role/)** *(2026 · 6 citations)* Multi-agent debate (MAD) is a popular test-time scaling technique for LLMs, but its standard form often does no better than a plain majority vote while costing more. 6. **[LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation](https://md.research.elamur.ai/free/en/papers/zhang-2026-lovec-reinforcement-learning-better-verbalized/)** *(2026)* LLMs often hallucinate in long factual answers. Most existing ways to flag unreliable content are post-hoc and expensive: they sample many responses or call an external model such as GPT-4 to split text into claims. LoVeC (Long-form Verbalized Confidence) instead trains a model to write a numerical confidence tag… ## Co-authors here 12 of 14 co-authors with a page, the most papers together first. - [Nigel Collier](https://md.research.elamur.ai/free/en/authors/nigel-collier/) ×6 - [Xiaochen Zhu](https://md.research.elamur.ai/free/en/authors/xiaochen-zhu/) ×4 - [Andreas Vlachos](https://md.research.elamur.ai/free/en/authors/andreas-vlachos/) ×3 - [Chengzu Li](https://md.research.elamur.ai/free/en/authors/chengzu-li/) ×2 - [Deqing Yang](https://md.research.elamur.ai/free/en/authors/deqing-yang/) ×2 - [Ruihan Yang](https://md.research.elamur.ai/free/en/authors/ruihan-yang/) ×2 - [Tom Stafford](https://md.research.elamur.ai/free/en/authors/tom-stafford/) ×2 - [Dong Yu](https://md.research.elamur.ai/free/en/authors/dong-yu/) - [Fangyu Liu](https://md.research.elamur.ai/free/en/authors/fangyu-liu/) - [Marco Basaldella](https://md.research.elamur.ai/free/en/authors/marco-basaldella/) - [Sen Yang](https://md.research.elamur.ai/free/en/authors/sen-yang/) - [Tiancheng Hu](https://md.research.elamur.ai/free/en/authors/tiancheng-hu/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×3: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/), [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×2 - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×2: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×2 - [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/): [EMNLP 2024](https://md.research.elamur.ai/free/en/venues/emnlp/2024/) ## Cited by Papers of our library cite their works 65 times (of the 149,439 papers whose bibliographies we read); [19 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/caiqi-zhang/cited-by/). Updated 2 November 2026