Papers by Yangyi Chen

17 papers
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework (2023.findings-acl)

Copied to clipboard

Challenge: Existing models of robustness evaluation are incomprehensive, impractical, and invalid .
Approach: They propose a framework for automatic robustness evaluation that shifts towards model-centric evaluation to further exploit the advantages of adversarial attacks.
Outcome: The proposed framework is based on a model-centric evaluation protocol and a robustness evaluation protocol.
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks (2022.emnlp-main)

Copied to clipboard

Challenge: Existing textual backdoor attacks are vulnerable to backdoors . researchers add extra training task to distinguish poisoned and clean data .
Approach: They propose two tricks that make existing backdoor attacks much more harmful . first trick is to add an extra task to distinguish poisoned and clean data . second trick is using all the clean training data rather than the original clean data.
Outcome: The proposed tricks can significantly improve attack performance in three tough situations including clean data fine-tuning, low-poisoning-rate, and label-consistent attacks.
Making Pre-trained Language Models both Task-solvers and Self-calibrators (2023.findings-acl)

Copied to clipboard

Challenge: Existing work shows that pre-trained language models can be effective for high-stake applications, but they become overconfident in their wrong predictions.
Approach: They propose to use extra data to train pre-trained language models to effectively utilize training samples to make them both task-solvers and self-calibrators.
Outcome: The proposed method can be used in three downstream applications, including selective classification, adversarial defense, and model cascading.
Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP (2022.emnlp-main)

Copied to clipboard

Challenge: Textual adversarial samples are often misrepresented in research on security, evaluation, explainability, and data augmentation.
Approach: They propose to use adversarial samples to evaluate their methods on security tasks to demonstrate the real-world concerns rather than developing impractical methods.
Outcome: The proposed method has higher practical value than the current benchmark.
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm (2022.findings-naacl)

Copied to clipboard

Challenge: Prompt-based learning inherits the vulnerability from pre-training, where model predictions can be misled by inserting triggers into the text.
Approach: They propose a potential solution to mitigate this vulnerability by injecting triggers into pre-trained language models using only plain text.
Outcome: The proposed learning paradigm inherits the vulnerability from the pre-training stage . it can totally control or severely decrease the performance of prompt-based models .
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for adversarial samples are poorly applied in computer vision . however, textual adversarials are still vulnerable to small perturbations .
Approach: They propose a framework to extend existing adversarial attack methods to textual adversarials by adding optimized perturbations to embedding layer and amplifying them in forward propagation process.
Outcome: The proposed framework achieves better performance even using proxy gradient information and produces more fluent and grammatical adversarial samples compared to baseline methods.
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (2021.emnlp-main)

Copied to clipboard

Challenge: Backdoor attacks can manipulate the output of deep neural networks and possess high insidiousness.
Approach: They propose a textual backdoor defense based on outlier word detection that can handle all the textual attacks.
Outcome: The proposed method can handle all the textual backdoor attack situations.
Automatic Construction of Sememe Knowledge Bases via Dictionaries (2021.findings-acl)

Copied to clipboard

Challenge: Sememe knowledge bases (SKBs) are used to analyze natural language processing.
Approach: They propose a method to build sememe knowledge bases from an existing dictionary . they propose to use existing dictionaries to build an English and a French SKB .
Outcome: The proposed method is superior to HowNet, the most widely used SKB that takes decades to build manually.
R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for instruction tuning force the model to complete a sentence no matter whether it knows the knowledge or not.
Approach: They propose a new approach to tuning large language models to refrain from answering questions beyond its parametric knowledge by identifying the disparity in parametric and parametric information.
Outcome: The proposed approach improves a model’s ability to answer known questions and refrain from answering unknown questions.
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach: They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome: The proposed training framework reduces the confidence calibration error and maintains the performance of the model.
A Close Look into the Calibration of Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty.
Approach: They conduct fine-grained control experiments to study the dynamic change in PLMs’ calibration performance in training.
Outcome: The proposed methods significantly reduce PLMs’ confidence in wrong predictions.
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for textual backdoor attacks insert additional contents into normal samples as triggers, causing detection and blocking of backdoors.
Approach: They propose to use syntactic structure as trigger in textual backdoor attacks . they propose to achieve similar attack performance but have higher invisibility .
Outcome: The proposed method achieves almost 100% success rate but has higher invisibility and stronger resistance to defenses than the insertion-based methods.
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer (2021.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer.
Approach: They propose to conduct adversarial and backdoor attacks based on text style transfer . the authors propose to use text style to alter the style of a sentence .
Outcome: The proposed methods show that popular models are vulnerable to both attacks based on text style transfer . the results show that the proposed methods perform better than baselines in many aspects .
Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are capable of performing tasks but are likely to be misused.
Approach: They propose a zero-shot black-box method to detect LLM-generated texts . they revise the text to be detected using the ChatGPT model .
Outcome: The proposed method can detect LLM-generated texts with a zero-shot black-box model . it is based on intuition that the model will make fewer revisions to LLMs than to human-written texts .
Multi-granularity Textual Adversarial Attack with Behavior Cloning (2021.emnlp-main)

Copied to clipboard

Challenge: Existing adversarial attack models are vulnerable to adversarials crafted by human-imperceptible perturbations.
Approach: They propose a multi-granularity adversarial attack model that generates high-quality adversarials with fewer queries to victim models.
Outcome: The proposed model generates high-quality adversarial samples with fewer queries to victim models compared to baseline models . the proposed model also reduces query times for black-box models that only output labels without confidence scores .
Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Vision-language models have demonstrated strong efficacy as visual assistants . however, evaluation of their reasoning capabilities requires a costly benchmark .
Approach: They propose a pipeline to measure the reasoning consistency of vision-language models . they propose supervised fine-tuning of VLMs and feedback from LLMs .
Outcome: The proposed framework reduces cost while ensuring the generation of a high-quality dataset.
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation (2023.emnlp-main)

Copied to clipboard

Challenge: State-of-the-art vision-language models have limited performance in structural knowledge extraction, such as relations between objects.
Approach: They propose to leverage the inherent structure of programming language to depict visual structural information in a well-organized structured format.
Outcome: The proposed framework improves visual structural knowledge extraction on visual structure prediction tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations