Zhijing Jin receives two best paper awards at NeurIPS 2024

The award for best paper at the NeurIPS 2024 Pluralistic Alignment Workshop was for the work described in "Language Model Alignment in Multilingual Trolley Problems", which can be viewed at https://arxiv.org/pdf/2407.02273. Zhijing Jin is first author on the paper, which is co-authored by Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi and Bernhard Schölkopf.

This success was followed by a second best paper award, selected from papers presented at NeurIPS 2024 Causality and Language Models Workshop. The award was made for the paper "Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias", which can be viewed at https://arxiv.org/pdf/2212.10678. Zhijing Jin is senior author on the paper, which is co-authored by Yuen Chen, Vethavikashini C R, Justus Mattern, Rada Mihalcea.

The research efforts of Zhijing Jin focus on natural language processing (NLP), large language models (LLMs), and causal inference. She recently graduated from the Max Planck Institute for Intelligent Systems as an ELLIS PhD, CLS associate doctoral fellow, and associate PhD with ETH AI Center. She is currently a postdoc at the Max Planck Institute for Intelligent Systems with Prof Bernhard Schölkopf, and is an awardee of the Postdoctoral Fellowship of the Future of Life Institute. From later this year, she will take on her role as an Assistant Professor at the University of Toronto, a Faculty Member at the Vector Institute and a CIFAR AI Chair, in the meantime as an ELLIS Advisor, and affiliated at the Max Planck Institute for Intelligent Systems.

Congratulations, Zhijing, on this very exciting and topical work!