Elamur Research⌕
☰
home / authors / Jason Cai

Jason Cai

Jason Cai has 3 papers in our library, in 2024–2026, most of them on Language models & pretraining, Summarization; often with Hang Su, Saab Mansour, Anna Currey.

3 papers in our library · 2024–2026

OpenAlex · ORCID · h-index 12 · 41 works · 1,032 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 78 times in our library · ⭐ Paper Stars ranking: #6618

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

🏥Massachusetts General HospitalBoston · United States2024–2026 · 5 paperscurrent🔬Mayo ClinicRochester · United States2019–2024 · 16 papers🏢AmazonSeattle · United States2024–2025 · 9 papers🏥Mayo Clinic in FloridaJacksonville · United States2020–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 works

🧭 Topics 2Research subjects and languages the work is about.Summarization · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20261 paper20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. FineSurE: Fine-grained Summarization Evaluation using LLMs (2024 · 92 citations)
    Evaluating summaries automatically remains difficult. ROUGE-style overlap metrics track human judgment poorly, and recent LLM judges such as G-Eval assign a single Likert score per summary, which hides where and how a summary fails. FineSurE addresses this by having an LLM run two fine-grained tasks. In fact…
  2. MemInsight: Autonomous Memory Augmentation for LLM Agents (2025 · 22 citations)
    LLM agents rely on long-term memory to give coherent, personalized answers. As stored interactions pile up, raw and unstructured memory becomes noisy and harder to search. MemInsight addresses this by having an LLM backbone enrich each memory entry automatically with attribute–value annotations, without a…
  3. Active Generalized Category Discovery with Diverse LLM Feedback (2026 · 1 citation)
    The paper addresses Generalized Category Discovery (GCD) for text. In GCD, a model must sort unlabeled data into both previously known and entirely new categories, using only a small labeled set drawn from the known ones. Earlier GCD approaches combine contrastive learning with K-Means++ clustering. Without extra…

 Co-authors here

12 of 13 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 78 times (of the 149,439 papers whose bibliographies we read); 19 citing papers with a page here →.

Updated

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