Skip to content

PhD at Max Planck Institute & ETH (2020-2024 expected)
👩‍🎓Google Scholar / 📁CV / twitter-icon@ZhijingJin
(The pronunciation of my name is close to “G-Gin Gin”)

I am a final-year PhD supervised by Bernhard Schoelkopf at Max Planck Institute & ETH, mentored by Rada Mihalcea (UMich), and co-supervised by Mrinmaya Sachan at ETH. I was fortunate to receive 3 Rising Star awards and 2 PhD Fellowships. Previously, I interned with Prof Mona Diab at Meta Responsible AI.

My research focuses on socially responsible NLP by causal inference. Specifically, I am active in (1) promoting NLP for social good, and (2) developing CausalNLP to improve robustness, fairness, and interpretability of NLP models, as well as analyze the causes of social problems.


Research Highlights

  • My technical work focuses on causal inference methods for NLP, specifically to address robustness [1,2,3,4], interpretability [4,5], and causal/logical reasoning [6,7,8,9] of LLMs. See my Keynote@EMNLP 2023 BlackboxNLP Workshop, Tutorial@EMNLP 2022, and talk slides.
  • I also extend the broader impact of Causal NLP to social good applications, with foundational work on NLP for Social Good (NLP4SG) framework [10,11; MIT News], social policy analysis [12,13], gender bias [14,15], and healthcare [16,17,18]. See my Talk@EMNLP 2022 NLP for Positive Impact Workshop, and 5 related workshops I’ve co-organized.
  • For community service, I co-organize the ACL Year-Round Mentorship (a network of 650+ mentees and 90+ NLP mentors), and provide research guidance [19] and career suggestions.

Selected Publications

For the complete list of my papers, please see my CV. For citation, feel free to use this .bib file.

CLadder: Assessing Causal Reasoning in Language Models
Zhijing Jin*, Yuen Chen*, Felix Leeb*, Luigi Gresele*, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
NeurIPS 2023 / Paper / Code

When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Zhijing Jin*, Sydney Levine*, Fernando Gonzalez*, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan†, Rada Mihalcea†, Josh Tenenbaum†, Bernhard Schoelkopf†
NeurIPS 2022 (Oral) / CogSci 2022 (Disciplinary Diversity and Integration Award) / Paper / Code / Slides / 5-Min Talk@NeurIPS / Twitter Thread / Invited Talk@CyberValley, Germany

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good
Fernando Gonzalez*, Zhijing Jin*, Jad Beydoun, Bernhard Schoelkopf, Tom Hope, Mrinmaya Sachan†, Rada Mihalcea†
EMNLP 2023 Findings / Paper / Code / Slides / Poster / Twitter Thread
Invited Talk at AI+X Summit at ETH

How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact
Zhijing Jin, Geeticka Chauhan, Brian Tse, Mrinmaya Sachan, Rada Mihalcea
Findings of ACL 2021 / Paper / Code / Poster / Slides / Talk / Tweet
MIT News article
Invited Talk at CyberValley, Germany

Logical Fallacy Detection
Zhijing Jin*, Abhinav Lalwani*, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schoelkopf
EMNLP 2022 Findings / Paper / Code / Slides / Video / Poster

Causation Between COVID Twitter Sentiments and Policies

Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US States
Zhijing Jin, Zeyu Peng, Tejas Vaidhya, Bernhard Schoelkopf, Rada Mihalcea
EMNLP 2021 Findings / Paper / Code / Poster / Slides / 7-Min Video

Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance
Jingwei Ni*, Zhijing Jin*, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf
NAACL 2022 (Oral) / Paper / Code / Slides / Twitter Thread / 13-Min Video

State-of-the-art generalisation research in NLP: a taxonomy and review
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, …, Ryan Cotterell, Zhijing Jin
Nature Machine Intelligence 2023 / Paper

Voices of Her: Analyzing Gender Differences in the AI Publication World
Yiwen Ding*, Jiarui Liu*, Zhiheng Lyu*, Kun Zhang, Bernhard Schoelkopf, Zhijing Jin†, Rada Mihalcea†
2022 / Paper

Independent Causal Mechanisms for NLP

Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
Zhijing Jin*, Julius von Kügelgen*, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf
EMNLP 2021 (Oral) / Paper / Code / Poster / Slides / 12-Min Video / Twitter Thread

TextGen Deep Learning for Text Style Transfer: A Survey
Di Jin*, Zhijing Jin*, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
CL Journal 2022 / Paper / Slides

Robust Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis
Xiaoyu Xing*, Zhijing Jin*, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang
EMNLP 2020 / Paper / Code / Slides

Robust Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
Di Jin*, Zhijing Jin*, Tianyi Joey Zhou, Peter Szolovits
AAAI 2020 (20.6%) / Paper / Code / Slides / Poster / MIT News / ACM TechNews / WeVolver / VentureBeat / Synced (Chinese)
Oral Presentation

TextGen IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation
Zhijing Jin*, Di Jin*, Jonas Mueller, Nicholas Matthews, Enrico Santus
EMNLP 2019 / Paper / Code / Poster

To follow talks on my research, please check out my YouTube.