馃コ our recent work is accepted to #EMNLP2025 main conference! In this paper, we leverage actionable interp insights to fix factual errors in multilingual LLMs 馃攳 Huge shoutout to @jenniferlumeng for her incredible work on this! She's applying for PhD this cycle and you should hire her ;) We will both be at NEMI this friday to present this work and other new things we are working on. Come talk to us!
馃Ever wonder why LLMs give inconsistent answers in different languages? In our paper, we identify two failure points in the multilingual factual recall process and propose fixes that guide LLMs to the "right path." This can boost performance by 35% in the weakest language! 馃搱
8
8
1
73
Woohoo congrats!!

Aug 20, 2025 路 7:45 PM UTC

1
2