Yapei Chang

About Me

Hi! I’m a PhD student at the University of Maryland, College Park, advised by Prof. Mohit Iyyer with a research focus on NLP. Prior to transferring to UMD, I was affiliated with the UMass Amherst NLP Lab, where I was also advised by Prof. Iyyer. My current main research interests include:

• Reliable / cost-effective metrics for LLM training [BLEUBERI (NeurIPS’25)] and evaluation [BooookScore (ICLR’24)]
• Scalable pipelines for building synthetic training [CLIPPER (COLM’25)] / evaluation data [ongoing work]

I like gaming and tinkering with mechanical keyboards in the free time I aggregate from my fluctuating work-life balance (it’s a work in progress ┐(‘～` )┌).

Updates

• [Jul 2025] Invited talk at the Google Multilinguality Reading Group
• [Jun 2025] Started my internship at Ai2 (OLMo team), working with Kyle Lo & Luca Soldaini!
• [May 2025] Released BLEUBERI, which shows that simple string-matching metrics like BLEU can be used as effective rewards for improving instruction following with GRPO, and can even match the performance of large reward models.
• [Feb. 2025] Released CLIPPER, which introduces a compression-based synthetic data generation pipeline for long-context narrative reasoning tasks.
• [Jan. 2025] Moved to UMD, College Park! Also got my MS degree from UMass Amherst.
• [Nov. 2024] ✈ Attended EMNLP to present PostMark, a paper on watermarking blackbox LLM outputs.
• [Oct. 2024] ✈ Attended COLM to present FABLES, a paper on faithfulness evaluation in book-length summarization.
• [May 2024] ✈ Attended ICLR and gave an oral presentation for BooookScore, a paper on book-length summarization and finegrained coherence evaluation.

Publications

Projects