Yangyi Chen

27 papers · 2021–2025 · 8 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🗺️ Taxonomy Completionist (34) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (8) 🧭 Keyword Pioneer

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (15) 🌱 Topic Pioneer ⚡ Prolific Year (5) 🗃️ Keyword Collector (94) 🔥 Unstoppable (5) 💎 Century Club (27) ❓ The Questioner

Conferences

EMNLP (8) ACL (6) NAACL (3) NIPS (3) ICLR (2) ICML (2) IJCNLP (2) CVPR (1)

Top co-authors

Zhiyuan Liu (15) Maosong Sun (13) Heng Ji (12) Lifan Yuan (9) Ganqu Cui (8) Xingyao Wang (8) Fanchao Qi (8) Hongcheng Gao (5) Mukai Li (4) Hao Peng (3)

Research topics

Privacy (1)

Keywords

backdoor attack (7) adversarial defense (5) natural language processing (4) adversarial attack (4) text classification (4) neural network (3) model security (3) reinforcement learning (3) adversarial learning (3) pre-trained language model (3) textual adversarial attack (3) nlp model (2) textual backdoor attack (2) model calibration (2) uncertainty quantification (2) nlp security (2) vision-language model (2) confidence estimation (2) adversarial perturbation (2) syntactic trigger (2)

Papers

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering ICML 2025 DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback CVPR 2024 Executable Code Actions Elicit Better LLM Agents ICML 2024 MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback ICLR 2024 CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets ICLR 2024 R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ NAACL 2024 SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales EMNLP 2024 Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models NAACL 2024 From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework ACL 2023 ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation EMNLP 2023 A Close Look into the Calibration of Pre-trained Language Models ACL 2023 Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework ACL 2023 Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT EMNLP 2023 Making Pre-trained Language Models both Task-solvers and Self-calibrators ACL 2023 Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations NIPS 2023 Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022 A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NIPS 2022 Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models NIPS 2022 Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP EMNLP 2022 Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022 Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer EMNLP 2021 Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP 2021 Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger IJCNLP 2021 Automatic Construction of Sememe Knowledge Bases via Dictionaries IJCNLP 2021 Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ACL 2021 Automatic Construction of Sememe Knowledge Bases via Dictionaries ACL 2021 ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021