arXiv subjects

Pengfei He

Publications and source records attributed to Pengfei He.

62 records · Page 4Linked to original sources

arXiv2024

Exploring Memorization in Fine-tuned Language Models

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during pre-training, the exploration of memorization during fine-tuning is rather limited. Compared to pre-training, fine-tuning typically involves more sensitive data and diverse objectives, thus may bring distinct privacy risks and unique memorization behaviors. In this work, we conduct the first comprehensive analysis to explore language models' (LMs) memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.

cs.AI↗

arXiv2024

Superiority of Multi-Head Attention in In-Context Linear Regression

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing literature predominantly focuses on the convergence of transformers with single-/multi-head attention, our research centers on comparing their performance. We conduct an exact theoretical analysis to demonstrate that multi-head attention with a substantial embedding dimension performs better than single-head attention. When the number of in-context examples D increases, the prediction loss using single-/multi-head attention is in O(1/D), and the one for multi-head attention has a smaller multiplicative constant. In addition to the simplest data distribution setting, we consider more scenarios, e.g., noisy labels, local examples, correlated features, and prior knowledge. We observe that, in general, multi-head attention is preferred over single-head attention. Our results verify the effectiveness of the design of multi-head attention in the transformer architecture.

cs.LG↗

arXiv2023

Probabilistic Categorical Adversarial Attack & Adversarial Training

The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration. Previously established methods leverage greedy search method, which can be very time-consuming to conduct successful attack. This also limits the development of adversarial training and potential defenses for categorical data. To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent. In our paper, we theoretically analyze its optimality and time complexity to demonstrate its significant advantage over current greedy based attacks. Moreover, based on our attack, we propose an efficient adversarial training framework. Through a comprehensive empirical study, we justify the effectiveness of our proposed attack and defense algorithms.

cs.LG↗

arXiv2023

On the Generalization of Training-based ChatGPT Detection Methods

ChatGPT is one of the most popular language models which achieve amazing performance on various natural language tasks. Consequently, there is also an urgent need to detect the texts generated ChatGPT from human written. One of the extensively studied methods trains classification models to distinguish both. However, existing studies also demonstrate that the trained models may suffer from distribution shifts (during test), i.e., they are ineffective to predict the generated texts from unseen language tasks or topics. In this work, we aim to have a comprehensive investigation on these methods' generalization behaviors under distribution shift caused by a wide range of factors, including prompts, text lengths, topics, and language tasks. To achieve this goal, we first collect a new dataset with human and ChatGPT texts, and then we conduct extensive studies on the collected dataset. Our studies unveil insightful findings which provide guidance for developing future methodologies or data collection strategies for ChatGPT detection.

cs.CL↗

arXiv2023

On profiniteness and Hausdorffness of topological residuated lattices

The aim of this paper is to study the profiniteness of compact topological residuated lattices and the existence of Hausdorff topological residuated lattices. Firstly, we study profinite residuated lattices and obtain sufficient and necessary conditions for profiniteness in compact topological residuated lattices. These conditions include topological and algebraic characterizations. Moreover, it order to study the existence of Hausdorf topological residuated lattices, we investigate finiteness conditions in residuated lattices. Finally, we investigate linear topological residuated lattices and give the class of residuated lattices that can be endowed with a non-trivial Hausdorff topology.

math.LO↗

arXiv2022

Large sample spectral analysis of graph-based multi-manifold clustering

In this work we study statistical properties of graph-based algorithms for multi-manifold clustering (MMC). In MMC the goal is to retrieve the multi-manifold structure underlying a given Euclidean data set when this one is assumed to be obtained by sampling a distribution on a union of manifolds $\mathcal{M} = \mathcal{M}_1 \cup\dots \cup \mathcal{M}_N$ that may intersect with each other and that may have different dimensions. We investigate sufficient conditions that similarity graphs on data sets must satisfy in order for their corresponding graph Laplacians to capture the right geometric information to solve the MMC problem. Precisely, we provide high probability error bounds for the spectral approximation of a tensorized Laplacian on $\mathcal{M}$ with a suitable graph Laplacian built from the observations; the recovered tensorized Laplacian contains all geometric information of all the individual underlying manifolds. We provide an example of a family of similarity graphs, which we call annular proximity graphs with angle constraints, satisfying these sufficient conditions. We contrast our family of graphs with other constructions in the literature based on the alignment of tangent planes. Extensive numerical experiments expand the insights that our theory provides on the MMC problem.

cs.LG↗

arXiv2022

Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering

Knowledge underpins reasoning. Recent research demonstrates that when relevant knowledge is provided as additional context to commonsense question answering (QA), it can substantially enhance the performance even on top of state-of-the-art. The fundamental challenge is where and how to find such knowledge that is high quality and on point with respect to the question; knowledge retrieved from knowledge bases are incomplete and knowledge generated from language models are inconsistent. We present Rainier, or Reinforced Knowledge Introspector, that learns to generate contextually relevant knowledge in response to given questions. Our approach starts by imitating knowledge generated by GPT-3, then learns to generate its own knowledge via reinforcement learning where rewards are shaped based on the increased performance on the resulting question answering. Rainier demonstrates substantial and consistent performance gains when tested over 9 different commonsense benchmarks: including 5 datasets that are seen during model training, as well as 4 datasets that are kept unseen. Our work is the first to report that knowledge generated by models that are orders of magnitude smaller than GPT-3, even without direct supervision on the knowledge itself, can exceed the quality of commonsense knowledge elicited from GPT-3.

cs.CL↗

arXiv2021

Detecting Extratropical Cyclones of the Northern Hemisphere with Single Shot Detector

In this paper, we propose a deep learning-based model to detect extratropical cyclones (ETCs) of northern hemisphere, while developing a novel workflow of processing images and generating labels for ETCs. We first label the cyclone center by adapting an approach from Bonfanti et.al. [1] and set up criteria of labeling ETCs of three categories: developing, mature, and declining stages. We then propose a framework of labeling and preprocessing the images in our dataset. Once the images and labels are ready to serve as inputs, we create our object detection model named Single Shot Detector (SSD) to fit the format of our dataset. We train and evaluate our model with our labeled dataset on two settings (binary and multiclass classifications), while keeping a record of the results. Finally, we achieved relatively high performance with detecting ETCs of mature stage (mean Average Precision is 86.64%), and an acceptable result for detecting ETCs of all three categories (mean Average Precision 79.34%). We conclude that the single-shot detector model can succeed in detecting ETCs of different stages, and it has demonstrated great potential in the future applications of ETC detection in other relevant settings.

cs.LG↗