paper-with-me

홈 › Papers

Artificial Text Detection via Examining the Topology of Attention Maps

2021-09-10 · EMNLP 2021 11 · Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the prominent performance of existing methods for artificial text detection, they still lack interpretability and robustness towards unseen models. To this end, we propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) which is currently understudied in the field of NLP. We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10\% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties. The results demonstrate that TDA is a promising line with respect to NLP tasks, specifically the ones that incorporate surface and structural information.

📄 PDF Abstract BibTeX arXiv:2109.04825

Code (2)

danchern97/tda4atd 공식 구현
upunaprosk/la-tda

Tasks

Text DetectionTopological Data Analysis

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Hallucination Detection in LLMs via Topological Divergence on Attention Graphs

2025-04-14 · Alexandra Bazarova, Aleksandr Yugay, Andrey Shulga, Alina Ermilova 외

Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, which leverages a…

HallucinationQuestion AnsweringRAG

Where to Pay Attention in Sparse Training for Feature Selection?

2022-11-26 · Ghada Sokar, Zahra Atashgahi, Mykola Pechenizkiy, Decebal Constantin Mocanu

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. …

feature selection

TopoBDA: Towards Bezier Deformable Attention for Road Topology Understanding

2024-12-25 · Muhammet Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, Alptekin Temizel

Understanding road topology is crucial for autonomous driving. This paper introduces TopoBDA (Topology with Bezier Deformable Attention), a novel approach that enhances road topology comprehension by leveraging Bezier De…

3D Lane DetectionLane Detection

Topology Imbalance and Relation Inauthenticity Aware Hierarchical Graph Attention Networks for Fake News Detection

2022-10-01 · COLING 2022 10 · Li Gao, Lingyun Song, Jie Liu, Bolin Chen 외

Fake news detection is a challenging problem due to its tremendous real-world political and social impacts. Recent fake news detection works focus on learning news features from News Propagation Graph (NPG). However, lit…

Fake News DetectionGraph AttentionRelation

RelTopo: Enhancing Relational Modeling for Driving Scene Topology Reasoning

2025-06-16 · Yueru Luo, Changqing Zhou, Yiming Yang, Erlong Li 외

Accurate road topology reasoning is critical for autonomous driving, enabling effective navigation and adherence to traffic regulations. Central to this task are lane perception and topology reasoning. However, existing …

Autonomous DrivingContrastive LearningLane Detection