Empirical Methods in Natural Language Processing (EMNLP) 2024

Apple is presenting new research at the Empirical Methods in Natural Language Processing (EMNLP) conference, which takes place in person in Miami, Florida, from November 12 – 16. We are proud to again sponsor the conference, which brings together the scientific and industrial research communities around natural language processing and artificial intelligence. Below is an overview of Apple’s participation at EMNLP 2024.

Accepted Papers

AGRaME: Any Granularity Ranking with Multi-Vector Embeddings

Saloni Potdar, Revanth Gangi Reddy, Omar Attia, Yunyao Li, Heng Ji

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models

Saloni Potdar, Ronak Pradeep, Daniel Lee, Ali Mousavi, Jeff Pound, Yisi Sang, Jimmy Lin, Ihab Ilyas, Mostafa Arefiyan Khalilabad, Yunyao Li

Divide-or-Conquer? Which Part Should You Distill Your LLM?

Yizhe Zhang, Zhuofeng Wu, Richard Bai, Aonan Zhang, Jiatao Gu, VG Vinod Vydiswaran, Navdeep Jaitly

MUSCLE: A Model Update Strategy for Compatible LLM Evolution

Hadi Pour Ansari, Jessica Echterhoff, Fartash Faghri, Raviteja Vemulapalli, Ting-Yao Hu, Chun-Liang Li, Oncel Tuzel

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization

Yong Lin, Skyler Seto, Maartje ter Hoeve, Rin Metcalf Susa, Barry Theobald, Xuan Wang, Yizhe Zhang, Chen Huang, Tong Zhang

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs

Saloni Potdar, Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Yunyao Li

Acknowledgements

Natalie Schluter is a Senior Area Chair.

Maartje ter Hoeve, Richard Bai, Saloni Potdar, and Sid Patwardhan are main conference area chairs.

Behrang Mohit, Hugh Ge, Kun Qian, Robin Schmidt, and Saloni Potdar are main conference reviewers.