Zhijing Jin

145 papers A* 14A 1B 2Journal 89Unranked 39
YearRankTypeTitle / Venue / Authors
2026 J jnl
BinaryPPO: Efficient Policy Optimization for Binary Classification.
CoRR
Punya Syon Pandey, Zhijing Jin
2026 J jnl
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs.
CoRR
Florent Draye, Abir Harrasse, Vedant Palit, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Schölkopf
2026 — conf
CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures.
EACL (Volume 1: Long Papers)
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin
2026 — conf
Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models.
EACL (Volume 1: Long Papers)
David Guzman Piedrahita, Irene Strauss, Rada Mihalcea, Zhijing Jin
2026 J jnl
Fluid Representations in Reasoning Models.
CoRR
Dmitrii Kharlapenko, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin
2026 J jnl
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory.
CoRR
Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren, Terry Jingchen Zhang, Zhijing Jin
2026 — conf
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities.
EACL (Volume 1: Long Papers)
Aly M. Kassem, Bernhard Schölkopf, Zhijing Jin
2026 J jnl
IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery.
CoRR
Ivaxi Sheth, Zhijing Jin, Bryan Wilder, Dominik Janzing, Mario Fritz
2026 — conf
NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment.
EACL (Volume 1: Long Papers)
Antonia Karamolegkou, Angana Borah, Eunjung Cho, Sagnik Ray Choudhury, Martina Galletti, Pranav Gupta, Oana Ignat, Priyanka Kargupta, Neema Kotonya, Hemank Lamba, Sun-Joo Lee, Arushi Mangla, Ishani Mondal, Fatima Zahra Moudakir, Deniz Nazar, Poli Nemkova, Dina Pisarevskaya, Naquee Rizwan, Nazanin Sabri, Keenan Samway, Dominik Stammbach, Anna Steinberg, David Tomás, Steven R. Wilson, Bowen Yi, Jessica H. Zhu, Arkaitz Zubiaga, Anders Søgaard, Alexander Fraser, Zhijing Jin, Rada Mihalcea, Joel R. Tetreault, Daryna Dementieva
2026 J jnl
Preserving Historical Truth: Detecting Historical Revisionism in Large Language Models.
CoRR
Francesco Ortu, Joeun Yook, Punya Syon Pandey, Keenan Samway, Bernhard Schölkopf, Alberto Cazzaniga, Rada Mihalcea, Zhijing Jin
2026 — conf
Taming Object Hallucinations with Verified Atomic Confidence Estimation.
EACL (Volume 1: Long Papers)
Jiarui Liu, Weihao Xuan, Zhijing Jin, Mona T. Diab
2026 J jnl
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering.
CoRR
Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla
2026 — conf
Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification.
EACL (Volume 1: Long Papers)
Paul He, Yinya Huang, Mrinmaya Sachan, Zhijing Jin
2026 J jnl
Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification.
CoRR
Paul He, Yinya Huang, Mrinmaya Sachan, Zhijing Jin
2026 — conf
When Do Language Models Endorse Limitations on Human Rights Principles?
EACL (Findings)
Keenan Samway, Miu Nicole Takagi, Rada Mihalcea, Bernhard Schölkopf, Ilias Chalkidis, Daniel Hershcovich, Zhijing Jin
2026 J jnl
When Do Language Models Endorse Limitations on Human Rights Principles?
CoRR
Keenan Samway, Miu Nicole Takagi, Rada Mihalcea, Bernhard Schölkopf, Ilias Chalkidis, Daniel Hershcovich, Zhijing Jin
2025 J jnl
Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability.
CoRR
Punya Syon Pandey, Samuel Simko, Kellin Pelrine, Zhijing Jin
2025 A* conf
Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models.
EMNLP
Younwoo Choi, Changling Li, Yongjin Yang, Zhijing Jin
2025 J jnl
Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models.
CoRR
Younwoo Choi, Changling Li, Yongjin Yang, Zhijing Jin
2025 J jnl
Are LLMs Good Safety Agents or a Propaganda Engine?
CoRR
Neemesh Yadav, Francesco Ortu, Jiarui Liu, Joeun Yook, Bernhard Schölkopf, Rada Mihalcea, Alberto Cazzaniga, Zhijing Jin
2025 A* conf
Are Language Models Consequentialist or Deontological Moral Reasoners?
EMNLP
Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin
2025 J jnl
Are Language Models Consequentialist or Deontological Moral Reasoners?
CoRR
Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin
2025 — conf
Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection.
IJCNLP-AACL (Findings)
Abhinav Lalwani, Tasha Kim, Lovish Chopra, Christopher Hahn, Zhijing Jin, Mrinmaya Sachan
2025 J jnl
CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures.
CoRR
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin
2025 J jnl
Can Theoretical Physics Research Benefit from Language Agents?
CoRR
Sirui Lu, Zhijing Jin, Terry Jingchen Zhang, Pavel Kos, J. Ignacio Cirac, Bernhard Schölkopf
2025 J jnl
Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models.
CoRR
Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz
2025 J jnl
Causality can systematically address the monsters under the bench(marks).
CoRR
Felix Leeb, Zhijing Jin, Bernhard Schölkopf
2025 J jnl
Causality for Natural Language Processing.
CoRR
Zhijing Jin
2025 — conf
Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias.
NAACL (Findings)
Yuen Chen, Vethavikashini Chithrra Raghuram, Justus Mattern, Rada Mihalcea, Zhijing Jin
2025 — conf
Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification.
EMNLP (System Demonstrations)
Chenfei Xiong, Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein, Lorena Calvo-Bartolomé, Alexander Miserlis Hoyle, Zhijing Jin, Mrinmaya Sachan, Markus Leippold, Dirk Hovy, Mennatallah El-Assady, Elliott Ash
2025 J jnl
Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification.
CoRR
Chenfei Xiong, Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein, Lorena Calvo-Bartolomé, Alexander Miserlis Hoyle, Zhijing Jin, Mrinmaya Sachan, Markus Leippold, Dirk Hovy, Mennatallah El-Assady, Elliott Ash
2025 J jnl
Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games.
CoRR
David Guzman Piedrahita, Yongjin Yang, Mrinmaya Sachan, Giorgia Ramponi, Bernhard Schölkopf, Zhijing Jin
2025 — conf
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal.
ACL (1)
Vaibhav Aggarwal, Ojasv Kamal, Abhinav Japesh, Zhijing Jin, Bernhard Schölkopf
2025 J jnl
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal.
CoRR
Vaibhav Aggarwal, Ojasv Kamal, Abhinav Japesh, Zhijing Jin, Bernhard Schölkopf
2025 J jnl
Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models.
CoRR
David Guzman Piedrahita, Irene Strauss, Bernhard Schölkopf, Rada Mihalcea, Zhijing Jin
2025 J jnl
Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap.
CoRR
Xuan Qi, Rongwu Xu, Zhijing Jin
2025 J jnl
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities.
CoRR
Aly M. Kassem, Bernhard Schölkopf, Zhijing Jin
2025 A* conf
Improving Large Language Model Safety with Contrastive Representation Learning.
EMNLP
Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
2025 J jnl
Improving Large Language Model Safety with Contrastive Representation Learning.
CoRR
Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
2025 A* conf
Language Model Alignment in Multilingual Trolley Problems.
ICLR
Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez Adauto, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf
2025 J jnl
NLP for Social Good: A Survey of Challenges, Opportunities, and Responsible Deployment.
CoRR
Antonia Karamolegkou, Angana Borah, Eunjung Cho, Sagnik Ray Choudhury, Martina Galletti, Rajarshi Ghosh, Pranav Gupta, Oana Ignat, Priyanka Kargupta, Neema Kotonya, Hemank Lamba, Sun-Joo Lee, Arushi Mangla, Ishani Mondal, Deniz Nazarova, Poli Nemkova, Dina Pisarevskaya, Naquee Rizwan, Nazanin Sabri, Dominik Stammbach, Anna Steinberg, David Tomás, Steven R. Wilson, Bowen Yi, Jessica H. Zhu, Arkaitz Zubiaga, Anders Søgaard, Alexander Fraser, Zhijing Jin, Rada Mihalcea, Joel R. Tetreault, Daryna Dementieva
2025 — conf
Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers.
ACL (5)
Luciana Benotti, Fanny Ducel, Karën Fort, Guido Ivetta, Zhijing Jin, Min-Yen Kan, Seunghun J. Lee, Minzhi Li, Margot Mieskes, Adriana S. Pagano
2025 — conf
Quriosity: Analyzing Human Questioning Behavior and Causal Inquiry through Curiosity-Driven Queries.
IJCNLP-AACL (Findings)
Roberto Ceraolo, Dmitrii Kharlapenko, Ahmad Khan, Amélie Reymond, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin
2025 — conf
Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing.
ACL (Findings)
Neemesh Yadav, Jiarui Liu, Francesco Ortu, Roya Ensafi, Zhijing Jin, Rada Mihalcea
2025 J jnl
Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing.
CoRR
Neemesh Yadav, Jiarui Liu, Francesco Ortu, Roya Ensafi, Zhijing Jin, Rada Mihalcea
2025 J jnl
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness.
CoRR
Yongjin Yang, Euiin Yi, Jongwoo Ko, Kimin Lee, Zhijing Jin, Se-Young Yun
2025 J jnl
SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests.
CoRR
Punya Syon Pandey, Hai Son Le, Devansh Bhardwaj, Rada Mihalcea, Zhijing Jin
2025 J jnl
Taming Object Hallucinations with Verified Atomic Confidence Estimation.
CoRR
Jiarui Liu, Weihao Xuan, Zhijing Jin, Mona T. Diab
2025 J jnl
The Curious Case of Curiosity across Human Cultures and LLMs.
CoRR
Angana Borah, Zhijing Jin, Rada Mihalcea
2025 — conf
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction.
ACL (Findings)
Yihuai Hong, Meng Cao, Dian Zhou, Lei Yu, Zhijing Jin
2025 J jnl
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction.
CoRR
Yihuai Hong, Dian Zhou, Meng Cao, Lei Yu, Zhijing Jin
2025 — conf
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST).
ACL (Findings)
Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona T. Diab
2025 J jnl
Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders.
CoRR
Abir Harrasse, Florent Draye, Zhijing Jin, Bernhard Schölkopf
2025 J jnl
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas.
CoRR
Steffen Backmann, David Guzman Piedrahita, Emanuel Tewolde, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin
2025 J jnl
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models.
CoRR
Francesco Ortu, Zhijing Jin, Diego Doimo, Alberto Cazzaniga
2025 A* conf
Why AI Is WEIRD and Shouldn't Be This Way: Towards AI for Everyone, with Everyone, by Everyone.
AAAI
Rada Mihalcea, Oana Ignat, Longju Bai, Angana Borah, Luis Chiruzzo, Zhijing Jin, Claude Kwizera, Joan Nwatu, Soujanya Poria, Thamar Solorio
2024 J jnl
A Randomized Controlled Trial on Anonymizing Reviewers to Each Other in Peer Review Discussions.
CoRR
Charvi Rastogi, Xiangchen Song, Zhijing Jin, Ivan Stelmakh, Hal Daumé III, Kun Zhang, Nihar B. Shah
2024 — conf
Analyzing the Role of Semantic Representations in the Era of Large Language Models.
NAACL-HLT
Zhijing Jin, Yuen Chen, Fernando Gonzalez Adauto, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona T. Diab
2024 J jnl
Analyzing the Role of Semantic Representations in the Era of Large Language Models.
CoRR
Zhijing Jin, Yuen Chen, Fernando Gonzalez, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona T. Diab
2024 — conf
Automatic Generation of Model and Data Cards: A Step Towards Responsible AI.
NAACL-HLT
Jiarui Liu, Wenkai Li, Zhijing Jin, Mona T. Diab
2024 J jnl
Automatic Generation of Model and Data Cards: A Step Towards Responsible AI.
CoRR
Jiarui Liu, Wenkai Li, Zhijing Jin, Mona T. Diab
2024 A* conf
Can Large Language Models Infer Causation from Correlation?
ICLR
Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona T. Diab, Bernhard Schölkopf
2024 J jnl
Causal Responsibility Attribution for Human-AI Collaboration.
CoRR
Yahang Qi, Bernhard Schölkopf, Zhijing Jin
2024 — conf
CausalCite: A Causal Formulation of Paper Citations.
ACL (Findings)
Ishan Kumar, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Negar Kiyavash, Mrinmaya Sachan, Bernhard Schölkopf
2024 J jnl
CausalQuest: Collecting Natural Causal Questions for AI Agents.
CoRR
Roberto Ceraolo, Dmitrii Kharlapenko, Amélie Reymond, Rada Mihalcea, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
2024 — conf
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals.
ACL (1)
Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf
2024 J jnl
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals.
CoRR
Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf
2024 J jnl
Cooperate or Collapse: Emergence of Sustainability Behaviors in a Society of LLM Agents.
CoRR
Giorgio Piatti, Zhijing Jin, Max Kleiman-Weiner, Bernhard Schölkopf, Mrinmaya Sachan, Rada Mihalcea
2024 A* conf
Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents.
NeurIPS
Giorgio Piatti, Zhijing Jin, Max Kleiman-Weiner, Bernhard Schölkopf, Mrinmaya Sachan, Rada Mihalcea
2024 — conf
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis.
EMNLP (Findings)
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez Adauto, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan
2024 — conf
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models.
LREC/COLING
Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan Nwatu, Verónica Pérez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea
2024 — conf
Implicit Personalization in Language Models: A Systematic Study.
EMNLP (Findings)
Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan
2024 J jnl
Implicit Personalization in Language Models: A Systematic Study.
CoRR
Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan
2024 — conf
Moûsai: Efficient Text-to-Music Diffusion Models.
ACL (1)
Flavio Schneider, Ojasv Kamal, Zhijing Jin, Bernhard Schölkopf
2024 J jnl
Multilingual Trolley Problems for Language Models.
CoRR
Zhijing Jin, Sydney Levine, Max Kleiman-Weiner, Giorgio Piatti, Jiarui Liu, Fernando Gonzalez Adauto, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf
2024 J jnl
NL2FOL: Translating Natural Language to First-Order Logic for Logical Fallacy Detection.
CoRR
Abhinav Lalwani, Lovish Chopra, Christopher Hahn, Caroline Trippel, Zhijing Jin, Mrinmaya Sachan
2024 A* conf
On Affine Homotopy between Language Encoders.
NeurIPS
Robin Chan, Reda Boumasmoud, Anej Svete, Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Mennatallah El-Assady, Ryan Cotterell
2024 J jnl
On Affine Homotopy between Language Encoders.
CoRR
Robin Chan, Reda Boumasmoud, Anej Svete, Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Mennatallah El-Assady, Ryan Cotterell
2024 J jnl
On the Causal Nature of Sentiment Analysis.
CoRR
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan
2024 A* conf
The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning.
EMNLP
Shaobo Cui, Zhijing Jin, Bernhard Schölkopf, Boi Faltings
2024 J jnl
The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning.
CoRR
Shaobo Cui, Zhijing Jin, Bernhard Schölkopf, Boi Faltings
2024 J jnl
Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset.
CoRR
Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona T. Diab
2024 J jnl
Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyone.
CoRR
Rada Mihalcea, Oana Ignat, Longju Bai, Angana Borah, Luis Chiruzzo, Zhijing Jin, Claude Kwizera, Joan Nwatu, Soujanya Poria, Thamar Solorio
2023 — conf
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models.
ACL (1)
Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
2023 J jnl
A PhD Student's Perspective on Research in NLP in the Era of Very Large Language Models.
CoRR
Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan Nwatu, Verónica Pérez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea
2023 J jnl
A taxonomy and review of generalization research in NLP.
Nat. Mac. Intell.
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos E. Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin
2023 — conf
ALERT: Adapt Language Models to Reasoning Tasks.
ACL (1)
Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona T. Diab, Asli Celikyilmaz
2023 J jnl
All Roads Lead to Rome? Exploring the Invariance of Transformers' Representations.
CoRR
Yuxin Ren, Qipeng Guo, Zhijing Jin, Shauli Ravfogel, Mrinmaya Sachan, Bernhard Schölkopf, Ryan Cotterell
2023 — conf
Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good.
EMNLP (Findings)
Fernando Gonzalez Adauto, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, Rada Mihalcea
2023 J jnl
Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good.
CoRR
Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, Rada Mihalcea
2023 A* conf
CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models.
NeurIPS
Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
2023 J jnl
CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models.
CoRR
Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, Bernhard Schölkopf
2023 J jnl
Can Large Language Models Infer Causation from Correlation?
CoRR
Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona T. Diab, Bernhard Schölkopf
2023 J jnl
CausalCite: A Causal Formulation of Paper Citations.
CoRR
Ishan Kumar, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Negar Kiyavash, Mrinmaya Sachan, Bernhard Schölkopf
2023 — conf
Membership Inference Attacks against Language Models via Neighbourhood Comparison.
ACL (Findings)
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
2023 J jnl
Membership Inference Attacks against Language Models via Neighbourhood Comparison.
CoRR
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
2023 J jnl
Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion.
CoRR
Flavio Schneider, Zhijing Jin, Bernhard Schölkopf
2023 J jnl
Natural Language Processing for Policymaking.
CoRR
Zhijing Jin, Rada Mihalcea
2023 J jnl
Navigating the Ocean of Biases: Political Bias Attribution in Language Models via Causal Structures.
CoRR
David F. Jenny, Yann Billeter, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin
2023 J jnl
OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models.
CoRR
Badr AlKhamissi, Siddharth Verma, Ping Yu, Zhijing Jin, Asli Celikyilmaz, Mona T. Diab
2023 J jnl
Psychologically-Inspired Causal Prompts.
CoRR
Zhiheng Lyu, Zhijing Jin, Justus Mattern, Rada Mihalcea, Mrinmaya Sachan, Bernhard Schölkopf
2023 J jnl
Voices of Her: Analyzing Gender Differences in the AI Publication World.
CoRR
Yiwen Ding, Jiarui Liu, Zhiheng Lyu, Kun Zhang, Bernhard Schölkopf, Zhijing Jin, Rada Mihalcea
2023 — conf
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP.
ACL (1)
Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan, Markus Leippold
2023 J jnl
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP.
CoRR
Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan, Markus Leippold
2022 J jnl
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models.
CoRR
Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
2022 — conf
CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing.
EMNLP (Tutorial Abstracts)
Zhijing Jin, Amir Feder, Kun Zhang
2022 B conf
Competing perspectives on building ethical AI: psychological, philosophical, and computational approaches.
CogSci
Sydney Levine, Zhijing Jin
2022 J jnl
Deep Learning for Text Style Transfer: A Survey.
Comput. Linguistics
Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2022 A* conf
Differentially Private Language Models for Secure Data Sharing.
EMNLP
Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf, Mrinmaya Sachan
2022 J jnl
Differentially Private Language Models for Secure Data Sharing.
CoRR
Justus Mattern, Zhijing Jin, Benjamin Weggenmann, Bernhard Schölkopf, Mrinmaya Sachan
2022 J jnl
Editing a Woman's Voice.
CoRR
Anna Costello, Ekaterina Fedorova, Zhijing Jin, Rada Mihalcea
2022 — conf
Logical Fallacy Detection.
EMNLP (Findings)
Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf
2022 J jnl
Logical Fallacy Detection.
CoRR
Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf
2022 — conf
Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance.
NAACL-HLT
Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf
2022 J jnl
Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance.
CoRR
Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf
2022 — conf
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang.
ACL (1)
Daphna Keidar, Andreas Opedal, Zhijing Jin, Mrinmaya Sachan
2022 J jnl
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang.
CoRR
Daphna Keidar, Andreas Opedal, Zhijing Jin, Mrinmaya Sachan
2022 J jnl
State-of-the-art generalisation research in NLP: a taxonomy and review.
CoRR
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin
2022 J jnl
Understanding Stereotypes in Language Models: Towards Robust Measurement and Zero-Shot Debiasing.
CoRR
Justus Mattern, Zhijing Jin, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schölkopf
2022 A* conf
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment.
NeurIPS
Zhijing Jin, Sydney Levine, Fernando Gonzalez Adauto, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Josh Tenenbaum, Bernhard Schölkopf
2022 J jnl
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment.
CoRR
Zhijing Jin, Sydney Levine, Fernando Gonzalez, Ojasv Kamal, Maarten Sap, Mrinmaya Sachan, Rada Mihalcea, Josh Tenenbaum, Bernhard Schölkopf
2021 — conf
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP.
EMNLP (1)
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf
2021 J jnl
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP.
CoRR
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf
2021 A conf
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings.
AISTATS
Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf
2021 — conf
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact.
ACL/IJCNLP (Findings)
Zhijing Jin, Geeticka Chauhan, Brian Tse, Mrinmaya Sachan, Rada Mihalcea
2021 J jnl
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact.
CoRR
Zhijing Jin, Geeticka Chauhan, Brian Tse, Mrinmaya Sachan, Rada Mihalcea
2021 J jnl
Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning.
CoRR
Hongru Wang, Zhijing Jin, Jiarun Cao, Gabriel Pui Cheong Fung, Kam-Fai Wong
2021 — conf
Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US States.
EMNLP (Findings)
Zhijing Jin, Zeyu Peng, Tejas Vaidhya, Bernhard Schölkopf, Rada Mihalcea
2020 J jnl
CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training.
CoRR
Qipeng Guo, Zhijing Jin, Xipeng Qiu, Weinan Zhang, David Wipf, Zheng Zhang
2020 J jnl
Deep Learning for Text Style Transfer: A Survey.
CoRR
Di Jin, Zhijing Jin, Zhiting Hu, Olga Vechtomova, Rada Mihalcea
2020 J jnl
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings.
CoRR
Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf
2020 B conf
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation.
COLING
Zhijing Jin, Qipeng Guo, Xipeng Qiu, Zheng Zhang
2020 A* conf
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles.
ACL
Di Jin, Zhijing Jin, Joey Tianyi Zhou, Lisa Orii, Peter Szolovits
2020 J jnl
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles.
CoRR
Di Jin, Zhijing Jin, Joey Tianyi Zhou, Lisa Orii, Peter Szolovits
2020 A* conf
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment.
AAAI
Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits
2020 J jnl
Relation of the Relations: A New Paradigm of the Relation Extraction Problem.
CoRR
Zhijing Jin, Yongyi Yang, Xipeng Qiu, Zheng Zhang
2020 — conf
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis.
EMNLP (1)
Xiaoyu Xing, Zhijing Jin, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang
2020 J jnl
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis.
CoRR
Xiaoyu Xing, Zhijing Jin, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang
2020 J jnl
Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation.
CoRR
Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits
2019 — conf
GraphIE: A Graph-Based Framework for Information Extraction.
NAACL-HLT (1)
Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, Regina Barzilay
2019 — conf
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation.
EMNLP/IJCNLP (1)
Zhijing Jin, Di Jin, Jonas Mueller, Nicholas Matthews, Enrico Santus
2019 J jnl
Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment.
CoRR
Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits
2019 J jnl
Unsupervised Text Style Transfer via Iterative Matching and Translation.
CoRR
Zhijing Jin, Di Jin, Jonas Mueller, Nicholas Matthews, Enrico Santus
2018 J jnl
3D Traffic Simulation for Autonomous Vehicles in Unity and Python.
CoRR
Zhijing Jin, Tristan Swedish, Ramesh Raskar
2018 J jnl
GraphIE: A Graph-Based Framework for Information Extraction.
CoRR
Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, Regina Barzilay