Jiaming Wang

Jiaming Wang has 2 papers in our library, in 2026, most of them on Language models & pretraining, Evaluation & benchmarks; often with Peng Ding, Xiaoyu Li, Xuezhi Cao.

2 papers in our library · 2026

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

Fields, topics and concepts

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

The most cited first (OpenAlex and our library).

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability (2026 · 1 citation)
Large language models often fail to satisfy every requirement in prompts that contain many constraints. Meeseeks is a benchmark that measures how far models can improve when they get repeated, targeted feedback. It works in cycles. The tested model answers a prompt, and each constraint is checked automatically. The…
SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026)
Most instruction-following benchmarks do not test whether LLMs can carry out the long, branching standard operating procedures (SOPs) used in real business workflows, where user input is often noisy.

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

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

Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 1 November 2026