Students frequently ask “what kind of research should we do in academia in the era of LLMs?”, my answer is very simple - work on harder problems that cannot be solved by LLMs alone in principle. Here is one such example - we developed “SmartBook”, a framework to automatically generate situation reports, a problem that cannot be solved by GPT-4 (comparison in Table 1 and Table 3).
The event extraction community has been stuck in using an 18 years old ACE data set with only 33 event types. It’s time to move on … we have developed a new dataset with 3,465 event types and 208K sentences, along with a high performing new system to extract them.
Check out this paper on General-Purpose Event Detection, led by the beyond amazing UIUC PhD student Zoey Li (she is on job market).
Watch out for my group's next faculty candidates: Yi R. Fung, Chi Han.
PhD graduate on Academic Job Market to start in Fall 2023: Manling Li - my absolutely best PhD graduate in my career so far, interview her before it's getting too late! She has been selected as EECS Rising Star, DARPA Riser and Microsoft PhD Fellow.
I have many post-doc, research scientist, RAs, software engineer positions and project managers available to work on information extraction related research on news domain and scientific domain, please drop me an email if interested.
Upcoming Tutorial at CVPR2023: "Knowledge-Driven Vision-Language Pretraining".
