Elamur Research⌕
☰
home / authors / Heli Qi

Heli Qi

Heli Qi has 4 papers in our library, in 2025–2026, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Evaluation & benchmarks; often with Qingcheng Zeng, Weihao Xuan, Junjue Wang.

4 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 6 · 17 works · 116 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 86 times in our library · 4 more in our library without a page yet · ⭐ Paper Stars ranking: #6983

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Waseda UniversityTokyo · Japan2025–2026 · 4 paperscurrent🔬RIKENWako · Japan2025–2026 · 3 paperscurrent🔬RIKEN Center for Advanced Intelligence ProjectTokyo · Japan2025–2026 · 2 paperscurrent🎓Nara Institute of Science and TechnologyIkoma · Japan2022–2025 · 6 papers

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 6The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksArts and Humanities · 3 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 3 worksInformation Systems · 1 work

🧭 Topics 5Research subjects and languages the work is about.Language models & pretraining · 2 worksReasoning · 2 worksEvaluation & benchmarks · 2 worksMultilingual & cross-lingual NLP · 2 worksVision & language · 1 work

 Works by year

2020s

20262 papers20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025 · 75 citations)
    Evaluating LLMs across languages has two gaps. Demanding reasoning benchmarks such as MMLU-Pro exist mainly in English. Multilingual suites like Global-MMLU combine translation sources of uneven quality and pose easier questions. The authors address both with MMLU-ProX, which carries the ten-option, reasoning-heavy…
  2. Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models (2025 · 11 citations)
    Vision-language models (VLMs) can state in plain language how sure they are of an answer. This study asks whether that stated confidence actually tracks how often they are correct. The authors evaluate verbalized calibration across three model families: instruction-tuned, text-reasoning, and visual-reasoning…
  3. The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents (2026 · 2 citations)
    The paper asks whether tool use always worsens how well LLM agents' stated confidence matches their real accuracy, or whether the effect depends on the tool.
  4. Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers (2026 · 1 citation)
    Search engines and RAG pipelines are mostly built and tested on single-language queries, yet many bilingual users mix languages when they search.

All works

8 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model EvaluationConference on Empirical Methods in Natural Language Processing (EMNLP)Weihao Xuan, Rui Yang, Heli Qi, et al.2025 · 75 citations
  2. USB: A Unified Semi-supervised Learning Benchmark for Classification ↗arXiv:2208.07204 · no summary yetYidong Wang et al.2022 · 61 citations
  3. Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Weihao Xuan, Qingcheng Zeng, Heli Qi, et al.2025 · 11 citations
  4. Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards ↗arXiv (Cornell University) · no summary yetFang Wu et al.2025 · 3 citations
  5. The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Weihao Xuan, Qingcheng Zeng, Heli Qi, et al.2026 · 2 citations
  6. Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current RetrieversFindings of the Association for Computational LinguisticsQingcheng Zeng, Yuheng Lu, Zeqi Zhou, et al.2026 · 1 citation
  7. Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations ↗arXiv (Cornell University) · no summary yetJunjue Wang et al.2026
  8. Proteo-R1: Reasoning Foundation Models for De Novo Protein Design ↗arXiv (Cornell University) · no summary yetFang Wu et al.2026

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 86 times (of the 149,439 papers whose bibliographies we read); 24 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/heli-qi/