Sign In

Yubin Kim

Applied AI/ML leader | Search/Recs expert

Yubin Kim is an Applied AI/ML leader with over 11 years of experience in machine learning, natural language processing, information retrieval, and recommendations. Kim has 4+ years of leadership experience, specializing in building collaborative, multi-disciplinary teams to address challenges at scale within large e-commerce and healthcare settings, focusing on driving business impact. Kim also possesses a strong research background with publications in renowned conferences and maintains active connections with academia.

Kim pursued a PhD at the Language Technologies Institute within the Computer Science department at Carnegie Mellon University. Additionally, Kim holds a Bachelor's degree in Software Engineering from the University of Waterloo.

Throughout Kim's career, they have held various roles at prominent organizations, including Head of Engineering at Vody, Senior Engineering Manager at Etsy, Director Of Technology at UPMC Enterprises, Senior Data Scientist at UPMC Enterprises, and intern positions at Microsoft Research, Google, and other tech firms. Kim has also served as a Graduate Research Assistant at Carnegie Mellon University and held research and software development roles during their academic journey.

Highlights

Jul 22 · linkedin

So I just realized that I spent the whole of #SIGIR2024 without up-to-date employment on LinkedIn! Now is a good time as any to announce that I've joined Vody in May.

We are a Gen AI start-up determined to make Gen AI actually useful for e-commerce. We have a lot of ideas, but our first product uses multimodal LLMs to fix missing/incorrect information in product catalogues, enriching product data with accurate, buyer-oriented descriptions extracted from a combination of visual/text modalities. And better data means better search, recs, SEO, etc.!

I attended SIGIR this year to get myself up-to-speed on LLMs (my background is in core information retrieval), especially how they're being used in industry. I was looking for ideas on: multimodal LLMs, training/finetuning tricks, prompting tricks, evaluation, LLMs in e-commerce. Keeping this in mind, here are my top takeaways from SIGIR:

Prompting LLMs for best results can be tricky

  • Getting good results with soft prompting is difficult and depends on a good starting state, which often requires internal knowledge about the LLM. And if you have the training data/GPUs, might as well finetune your LLM instead of learning a better soft prompt! (This, of course, changes if you don't have the GPUs or you're using closed-source models.)
  • Having said that, trying a bunch of different hard prompt variations and picking the best one is easy. So you should do it. 
  • When fine-tuning, use varying prompts. Also, if you're supplying a list of in-context information, shuffle the list.
  • Chain-of-thought is good. The general concept of breaking down the problem for LLMs is very useful for getting better performance and is used across the board, including in LLM-based evaluation.
  • Shout-out to the MSFT folks for including a detailed treatment of their prompting strategy in their paper "Large Language Models can Accurately Predict Searcher Preferences" https://lnkd.in/efxB6-A5
  • I learned about DSPy (https://lnkd.in/eAQtmdP3), a prompt optimization framework, and I'm excited to try it!

Using LLMs for synthetic search/recs training data generation improves models

  • Many industry folks are seeing great results with training their search models on LLM-generated queries, including Spotify (https://lnkd.in/eWaBA3zE), Apple (https://lnkd.in/eJb-W-VT), Comcast (https://lnkd.in/ek3uycF6).
  • Best results seem to be when query generation is guided
  • Many recommender systems papers are successfully using LLMs to simulate user behavior to generate more training data

Part 2 and 3 are in comments due to character restriction!

Jul 18 · linkedin

I'll be spending the last day at #SIGIR2024 at the workshop I'm co-organizing with Surya Kallumadi, Tracy Holloway King, Vamsi Salaka, Maarten de Rijke. Come to our SIGIR 2024 Workshop on eCommerce!

Yubin Kim
Add to my network

Location

Pittsburgh, Pennsylvania, United States