Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models.

[BibT_eX]

[DOI]

Yangyi Chen

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

MIRACLE: An Online, Explainable Multimodal Interactive Concept Learning System.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Executable Code Actions Elicit Better LLM Agents.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

DRESS : Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training.

[BibT_eX]

[DOI]

Trans. Assoc. Comput. Linguistics, 2023

Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown.

[BibT_eX]

[DOI]

CoRR, 2023

R-Tuning: Teaching Large Language Models to Refuse Unknown Questions.

[BibT_eX]

[DOI]

CoRR, 2023

Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations.

[BibT_eX]

[DOI]

CoRR, 2023

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

A Close Look into the Calibration of Pre-trained Language Models.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

Making Pre-trained Language Models both Task-solvers and Self-calibrators.

[BibT_eX]

[DOI]

Yangyi Chen

Xingyao Wang

Heng Ji

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2022, 2022

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks.

[BibT_eX]

[DOI]

CoRR, 2021

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Multi-granularity Textual Adversarial Attack with Behavior Cloning.

[BibT_eX]

[DOI]

Yangyi Chen

Jin Su

Wei Wei

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

QoE-Fairness Tradeoff Scheme for Dynamic Spectrum Allocation Based on Deep Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the CSAE 2021: The 5th International Conference on Computer Science and Application Engineering, Sanya, China, October 19, 2021

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger.

[BibT_eX]

[DOI]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

Automatic Construction of Sememe Knowledge Bases via Dictionaries.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, 2021

2020

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.