🧑‍🔬 Zhijing Jin

🏛️ Affiliations

🎓University of TorontoToronto · Canada2020–2026 · 36 papersEmployment · Assistant Professor, Computer Sciencecurrent🔬Max Planck Institute for Intelligent SystemsStuttgart · Germany2021–2026 · 30 papersEmploymentcurrent🔬Max Planck SocietyMunich · Germany2020–2026 · 18 paperscurrent🔬Vector InstituteToronto · Canada2025–2026 · 8 paperscurrent🎓ETH ZurichZurich · Switzerland2021–2025 · 45 papers🎓University of Hong KongPok Fu Lam · Hong Kong2018–2020 · 6 papers🎓University of MichiganAnn Arbor · United States2022–2024 · 5 papers🎓Carnegie Mellon UniversityPittsburgh · United States2026 · 3 papers🏢Intelligent Systems ResearchThousand Oaks · United States2023–2026 · 3 papers🎓Stanford UniversityStanford · United States2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment (2019 · 1,326 citations)
   NLP classifiers, including pre-trained BERT, can be fooled by small edits to their input. Building such adversarial text is harder than for images because language is discrete, and the edits must keep the meaning, the grammar and the label a human would assign. The authors introduce TextFooler, a black-box attack…
2. Membership Inference Attacks against Language Models via Neighbourhood Comparison (2023 · 162 citations)
   The paper examines membership inference attacks (MIAs) on language models, which try to determine whether a specific text was part of a model's training set.
3. Logical Fallacy Detection (2022 · 119 citations)
   The authors introduce logical fallacy detection as a new NLP task: classifying an argument by the type of flawed reasoning it contains.
4. A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models (2023 · 65 citations)
   Large language models perform well on math benchmarks, but it is unclear whether they truly reason or exploit superficial cues in problem wording.

All works

19 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentDi Jin, Zhijing Jin, Joey Tianyi Zhou, et al.Proceedings of the AAAI Conference on Artificial Intelligence · 1,326 citations
2. Deep Learning for Text Style Transfer: A Survey · original ↗ · no summary yet · Computational LinguisticsDi Jin et al.2022 · 316 citations
3. Membership Inference Attacks against Language Models via Neighbourhood ComparisonJustus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, et al.Findings of the Association for Computational Linguistics · 162 citations
4. Logical Fallacy DetectionZhijing Jin, Abhinav Lalwani, Tejas Vaidhya, et al.Findings of the Association for Computational Linguistics · 119 citations
5. A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language ModelsAlessandro Stolfo, Zhijing Jin, Kumar Shridhar, et al.Annual Meeting of the Association for Computational Linguistics (ACL) · 65 citations
6. CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training · original ↗ · no summary yet · Proceedings of the 3rd International Workshop on Natural Language Generation…Qipeng Guo et al.2020 · 61 citations
7. GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation · original ↗ · no summary yet · Proceedings of the 28th International Conference on Computational LinguisticsZhijing Jin et al.2020 · 58 citations
8. Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals · original ↗ · no summary yet · Proceedings of the 62nd Annual Meeting of the Association for Computational…Francesco Ortu et al.2024 · 22 citations
9. Language Model Alignment in Multilingual Trolley Problems · original ↗ · no summary yet · arXiv:2407.02273Zhijing Jin et al.2024 · 21 citations
10. Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection · original ↗ · no summary yet · arXiv:2405.02318Abhinav Lalwani et al.2024 · 15 citations
11. Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis · original ↗ · no summary yet · arXiv:2311.08605David F. Jenny et al.2023 · 6 citations
12. DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal · original ↗ · no summary yet · Proceedings of the 63rd Annual Meeting of the Association for Computational…Vaibhav Aggarwal et al.2025 · 4 citations
13. Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models · original ↗ · no summary yet · Proceedings of the 19th Conference of the European Chapter of the Association…David Guzman Piedrahita et al.2026 · 3 citations
14. When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models · original ↗ · no summary yet · Proceedings of the 64th Annual Meeting of the Association for Computational…Francesco Ortu et al.2026 · 2 citations
15. PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf · original ↗ · no summary yet · Proceedings of the 64th Annual Meeting of the Association for Computational…Jiarui Liu et al.2026 · 1 citation
16. When Do Language Models Endorse Limitations on Human Rights Principles? · original ↗ · no summary yet · Findings of the Association for Computational Linguistics: EACL 2026Keenan Samway et al.2026 · 1 citation
17. Test of Time: Rethinking Temporal Signal of Benchmark Contamination · original ↗ · no summary yet · Proceedings of the 64th Annual Meeting of the Association for Computational…Terry Jingchen Zhang et al.2026 · 1 citation
18. Taming Object Hallucinations with Verified Atomic Confidence Estimation · original ↗ · no summary yet · Proceedings of the 19th Conference of the European Chapter of the Association…Jiarui Liu et al.2026
19. CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures · original ↗ · no summary yet · Proceedings of the 19th Conference of the European Chapter of the Association…Punya Syon Pandey et al.2026

🤝 Co-authors here

12 co-authors with a page, the most papers together first.

• Bernhard Schölkopf ×3
• Mrinmaya Sachan ×3
• Alessandro Stolfo
• Di Jin
• Fatemehsadat Mireshghallah
• Joey Tianyi Zhou
• Kumar Shridhar
• Peter Szolovits
• Rada Mihalcea
• Taylor Berg-Kirkpatrick
• Xiaoyu Shen
• Yiwen Ding

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×6: ACL 2023
• Proceedings of the 19th Conference of the European Chapter… ×3
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2023, Findings of the Association for Computational Linguistics 2022
• Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2019
• Computational Linguistics
• Findings of the Association for Computational Linguistics…
• Proceedings of the 28th International Conference on…
• Proceedings of the 3rd International Workshop on Natural…

🔗 Cited by

Papers of our library cite their works 875 times (of the 141,840 papers whose bibliographies we read); 61 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhijing-jin/