6 papers
Pigeonholing: how bad prompts hurt models, causing collapse and mistakes
Hyunji Nam, Keertana Chidambaram, Dorottya Demszky +1
While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call…
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
Hyunji Nam, Haoran Li, Natasha Jaques
While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existi…
Netflix Artwork Personalization via LLM Post-training
Hyunji Nam, Sejoon Oh, Emma Kong +2
Large language models (LLMs) have demonstrated success in various applications of user recommendation and personalization across e-commerce and entertainment. On many entertainment…
IDEAlign: Comparing Ideas of Large Language Models to Domain Expert
Hyunji Nam, Lucia Langlois, James Malamut +2
Large language models (LLMs) are increasingly used to produce open-ended, interpretive annotations, yet there is no validated, scalable measure of idea-level similarity to expert a…
Learning to summarize user information for personalized reinforcement learning from human feedback
Hyunji Nam, Yanming Wan, Mickel Liu +3
As everyday use cases of large language model (LLM) AI assistants have expanded, it is becoming increasingly important to personalize responses to align to different users' prefere…
EduCoder: An Open-Source Annotation System for Education Transcript Data
Saad Ashraf, James Malamut, Vishal Kumar +7
We introduce EduCoder, a domain-specialized tool designed to support utterance-level annotation of educational dialogue. While general-purpose text annotation tools for NLP and qua…