UCLA NLP Seminar - Yulia Tsvetkov - Optimizing for Long-Term Vision in a Fast-Paced Research World

Talk Title: Optimizing for Long-Term Vision in a Fast-Paced Research World

Abstract: The fast-paced race for larger language models—and the promise of financial gains for the winners—incentivizes heavier engineering with incremental ideas, often at the expense of long-term vision. While this approach advances industry products used by millions, it is not necessarily the right approach for academic research. In this talk, I will present novel task formulations and evaluation benchmarks that question mainstream assumptions about LLM architectures, training/alignment algorithms, and evaluation approaches. While proposed ideas contradict the common practice, they expose blind spots in LLMs reasoning abilities, and huge performance and fairness gaps in best commercial LLMs, highlighting directions for future research.

To checkout other talks in our full NLP Seminar Series, please visit:    • Playlist