🧑‍🔬 Lingjiao Chen

🏛️ Affiliations

🎓Stanford UniversityStanford · United States2021–2026 · 14 papersEmployment · Computer Sciences🎓University of Wisconsin–MadisonMadison · United States2017–2019 · 10 papers🎓University of Electronic Science and Technology of ChinaChengdu · China2014–2018 · 8 papers🏢MicrosoftRedmond · United States2024–2026 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance (2023 · 241 citations)
   Commercial LLM APIs differ widely in price and quality, and running the strongest model on every query quickly becomes costly for high-volume uses such as customer support.
2. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews (2024 · 119 citations)
   Detecting LLM-written text one document at a time is unreliable, and humans perform barely better than chance at it.
3. Phi-4-reasoning Technical Report (2025 · 64 citations)
   The report asks whether a compact model can match much larger systems on hard multi-step reasoning. Microsoft researchers fine-tuned the 14B-parameter Phi-4 on more than 1.4M prompts paired with long reasoning traces written by o3-mini. The result is Phi-4-reasoning. The prompts were chosen to be "teachable": varied…

All works

9 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving PerformancearXiv:2305.05176Lingjiao Chen, Matei Zaharia, James Zou2023 · 241 citations
2. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer ReviewsarXiv:2403.07183Weixin Liang, Zachary Izzo, Yaohui Zhang, et al.2024 · 119 citations
3. Phi-4-reasoning Technical ReportarXiv:2504.21318Marah Abdin, Sahaj Agarwal, Ahmed Awadallah, et al.2025 · 64 citations
4. Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems ↗arXiv (Cornell University) · no summary yetLingjiao Chen et al.2024 · 46 citations
5. Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems ↗neural information processing systems · no summary yetLingjiao Chen et al.2024 · 27 citations
6. Optimizing Model Selection for Compound AI Systems ↗arXiv (Cornell University) · no summary yetLingjiao Chen et al.2025 · 9 citations
7. BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation ↗arXiv (Cornell University) · no summary yetZhu, Alan et al.2025 · 6 citations
8. Specifications: The missing link to making the development of LLM systems an engineering discipline ↗arXiv (Cornell University) · no summary yetIon Gabriel Stoica et al.2024 · 4 citations
9. The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More ↗arXiv (Cornell University) · no summary yetLingjiao Chen et al.2026 · 1 citation

🤝 Co-authors here

12 of 19 co-authors with a page, the most papers together first.

• James Zou ×2
• Ahmed Hassan Awadallah
• Daniel A. McFarland
• Haley Lepp
• Hancheng Cao
• Haotian Ye
• Harkirat Behl
• Marah Abdin
• Matei Zaharia
• Mojan Javaheripi
• Piero Kauffmann
• Sahaj Agarwal

Venues

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

• neural information processing systems

🔗 Cited by

Papers of our library cite their works 380 times (of the 149,439 papers whose bibliographies we read); 96 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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