Search Results for author:
Found 104 papers, 55 papers with code
On the Shortcut Learning in Multilingual Neural Machine Translation
By carefully designing experiments on different MNMT scenarios and models, we attribute the off-target issue to the overfitting of the shortcuts of (non-centric, centric) language mappings.
Interaction2Code: How Far Are We From Automatic Interactive Webpage Generation?
To fill in the blank, we present the first systematic investigation of MLLMs in generating interactive webpages.
Enhancing Temporal Modeling of Video LLMs via Time Gating
However, most existing Video LLMs neglect temporal information in video data, leading to struggles with temporal-aware video understanding.
Contextualized Data-Wrangling Code Generation in Computational Notebooks
With CoCoMine, we construct CoCoNote, a dataset containing 58, 221 examples for Contextualized Data-wrangling Code generation in Notebooks.
Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis
In the second stage, LoFI leverages a pre-trained language model with a novel prompt-based tuning method to extract fine-grained information of interest from the collected logs.
Learning to Ask: When LLMs Meet Unclear Instruction
Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone.
Making Long-Context Language Models Better Multi-Hop Reasoners
Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications.
On the Resilience of Multi-Agent Systems with Malicious Agents
Additionally, we show the promise of improving multi-agent system resilience by demonstrating that two defense methods, introducing a mechanism for each agent to challenge others' outputs, or an additional agent to review and correct messages, can enhance system resilience.
Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach
We conduct extensive testing with a dataset comprised of real-world websites and various MLLMs and demonstrate that DCGen achieves up to a 14% improvement in visual similarity over competing methods.
Automatic Programming: Large Language Models and Beyond
In this article, we study automated coding in a general sense and study the concerns around code quality, security and related issues of programmer responsibility.
How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO
However, existing studies focus on imitating well-known public figures or fictional characters, overlooking the potential for simulating ordinary individuals.
Beyond Embeddings: The Promise of Visual Table in Visual Reasoning
Visual representation learning has been a cornerstone in computer vision, involving typical forms such as visual embeddings, structural symbols, and text-based representations.
Ranked #85 on
Visual Question Answering
on MM-Vet
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Researchers have examined LLMs' decision-making through the lens of Game Theory.
Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach
We also share our experience in deploying COLA in our real-world cloud system, Cloud X.
FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systems
To date, FaultProfIT has analyzed 10, 000+ incidents from 30+ cloud services, successfully revealing several fault trends that have informed system improvements.
A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models
The significant breakthroughs of Medical Multi-Modal Large Language Models (Med-MLLMs) renovate modern healthcare with robust information synthesis and medical decision support.
Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context
We conducted preliminary experiments to validate the performance of IDECoder and observed that this synergy represents a promising trend for future exploration.
MTAD: Tools and Benchmarks for Multivariate Time Series Anomaly Detection
These methods are evaluated with five multivariate KPI datasets that are publicly available.
New Job, New Gender? Measuring the Social Bias in Image Generation Models
BiasPainter uses a diverse range of seed images of individuals and prompts the image generation models to edit these images using gender, race, and age-neutral queries.
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4.
The Earth is Flat? Unveiling Factual Errors in Large Language Models
Current methods for evaluating LLMs' veracity are limited by test data leakage or the need for extensive human labor, hindering efficient and accurate error detection.
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models
This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e. g., ChatGPT).
All Languages Matter: On the Multilingual Safety of Large Language Models
In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice.
Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench
Large Language Models (LLMs) have recently showcased their remarkable capacities, not only in natural language processing tasks but also across diverse domains such as clinical medicine, legal consultation, and education.
Practical Anomaly Detection over Multivariate Monitoring Metrics for Online Services
As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems' health status, becomes more and more critical and challenging.
An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software
Moreover, through retraining the models with the test cases generated by OASIS, the robustness of the moderation model can be improved without performance degradation.
VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control
In particular, our VL-PET-large with lightweight PET module designs significantly outperforms VL-Adapter by 2. 92% (3. 41%) and LoRA by 3. 37% (7. 03%) with BART-base (T5-base) on image-text tasks.
CLEVA: Chinese Language Models EVAluation Platform
With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue.
Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
Evaluating Large Language Models' (LLMs) anthropomorphic capabilities has become increasingly important in contemporary discourse.
On the Robustness of Latent Diffusion Models
Therefore, in this paper, we aim to analyze the robustness of latent diffusion models more thoroughly.
Log-based Anomaly Detection based on EVT Theory with feedback
System logs play a critical role in maintaining the reliability of software systems.
Revisiting the Reliability of Psychological Scales on Large Language Models
Recent research has focused on examining Large Language Models' (LLMs) characteristics from a psychological standpoint, acknowledging the necessity of understanding their behavioral characteristics.
Improving the Transferability of Adversarial Samples by Path-Augmented Method
However, such methods selected the image augmentation path heuristically and may augment images that are semantics-inconsistent with the target images, which harms the transferability of the generated adversarial samples.
Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
However, the variance of the back-propagated gradients in intermediate blocks of ViTs may still be large, which may make the generated adversarial samples focus on some model-specific features and get stuck in poor local optima.
Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attention
Our study demonstrates that logs and metrics can manifest system anomalies collaboratively and complementarily, and neither of them only is sufficient.
Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation
Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text.
No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence
Besides, the performance of fine-tuning strongly relies on the amount of downstream data, while in practice, the scenarios with scarce data are common.
Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text.
Understanding and Mitigating the Uncertainty in Zero-Shot Translation
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system.
AEON: A Method for Automatic Evaluation of NLP Test Cases
However, in practice, many of the generated test cases fail to preserve similar semantic meaning and are unnatural (e. g., grammar errors), which leads to a high false alarm rate and unnatural test cases.
Text Revision by On-the-Fly Representation Optimization
In this approach, we simply fine-tune a pre-trained Transformer with masked language modeling and attribute classification.
Improving Adversarial Transferability via Neuron Attribution-Based Attacks
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples.
Accelerating Code Search with Deep Hashing and Code Classification
Code search is to search reusable code snippets from source code corpus based on natural languages queries.
FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows
Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it.
Towards Efficient Post-training Quantization of Pre-trained Language Models
Experiments on GLUE and SQuAD benchmarks show that our proposed PTQ solution not only performs close to QAT, but also enjoys significant reductions in training time, memory overhead, and data consumption.
Graph-based Incident Aggregation for Large-Scale Online Service Systems
The proposed framework is evaluated with real-world incident data collected from a large-scale online service system of Huawei Cloud.
Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection
To better understand the characteristics of different anomaly detectors, in this paper, we provide a comprehensive review and evaluation of five popular neural networks used by six state-of-the-art methods.
Improving the Transferability of Adversarial Samples With Adversarial Transformations
Although deep neural networks (DNNs) have achieved tremendous performance in diverse vision challenges, they are surprisingly susceptible to adversarial examples, which are born of intentionally perturbing benign samples in a human-imperceptible fashion.
Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation
Then, a self-supervised learning framework is constructed: confident predictions from teacher models are served as annotations to guide the student model to learn optical flow for those less confident predictions.
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.
Code Structure Guided Transformer for Source Code Summarization
Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance.
Open-Retrieval Conversational Machine Reading
On our created OR-ShARC dataset, MUDERN achieves the state-of-the-art performance, outperforming existing single-passage conversational machine reading models as well as a new multi-passage conversational machine reading baseline by a large margin.
Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
Further analyses show that our multi-head attention is able to attend information from various aspects and boost classification or generation in diverse scenarios.
Effective Data-aware Covariance Estimator from Compressed Data
Estimating covariance matrix from massive high-dimensional and distributed data is significant for various real-world applications.
Making Online Sketching Hashing Even Faster
Data-dependent hashing methods have demonstrated good performance in various machine learning applications to learn a low-dimensional representation from the original data.
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information.
Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
Besides a small number of high-resource sentence functions, a large portion of sentence functions is infrequent.
Exploiting Unsupervised Data for Emotion Recognition in Conversations
Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task.
Emotion Recognition in Conversation
General Classification
+2
Emerging App Issue Identification via Online Joint Sentiment-Topic Tracing
Experiments on popular apps from Google Play and Apple's App Store demonstrate the effectiveness of MERIT in identifying emerging app issues, improving the state-of-the-art method by 22. 3% in terms of F1-score.
Loghub: A Large Collection of System Log Datasets for AI-driven Log Analytics
To fill this significant gap and facilitate more research on AI-driven log analytics, we have collected and released loghub, a large collection of system log datasets.
Software Engineering
Photon: A Robust Cross-Domain Text-to-SQL System
Natural language interfaces to databases (NLIDB) democratize end user access to relational data.
Unsupervised Text Generation by Learning from Search
In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search.
EMT: Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.
VD-BERT: A Unified Vision and Dialog Transformer with BERT
By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks.
Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models
In this paper, we bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table -- an interpretable table of bilingual lexicons.
Why an Android App is Classified as Malware? Towards Malware Classification Interpretation
In this paper, to fill this gap, we propose a novel and interpretable ML-based approach (named XMal) to classify malware with high accuracy and explain the classification result meanwhile.
What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process
In our world with full of uncertainty, debates and argumentation contribute to the progress of science and society.
Automating App Review Response Generation
Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app.
Neuron Interaction Based Representation Composition for Neural Machine Translation
Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors.
Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network
We propose an Attention Gated Hierarchical Memory Network (AGHMN) to address the problems of prior work: (1) Commonly used convolutional neural networks (CNNs) for utterance feature extraction are less compatible in the memory modules; (2) Unidirectional gated recurrent units (GRUs) only allow each historical utterance to have context before it, preventing information propagation in the opposite direction; (3) The Soft Attention for summarizing loses the positional and ordering information of memories, regardless of how the memory bank is built.
Ranked #50 on
Emotion Recognition in Conversation
on IEMOCAP
Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling
Word2Vec is the most popular model for word representation and has been widely investigated in literature.
PT-CoDE: Pre-trained Context-Dependent Encoder for Utterance-level Emotion Recognition
Witnessing the success of transfer learning in natural language process (NLP), we propose to pre-train a context-dependent encoder (CoDE) for ULER by learning from unlabeled conversation data.
Improving Question Generation With to the Point Context
Question generation (QG) is the task of generating a question from a reference sentence and a specified answer within the sentence.
Logzip: Extracting Hidden Structures via Iterative Clustering for Log Compression
Data compression is essential to reduce the cost of log storage.
Databases Software Engineering
Towards Understanding Neural Machine Translation with Word Importance
Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory.
An Online Topic Modeling Framework with Topics Automatically Labeled
In this paper, we propose a novel online topic tracking framework, named IEDL, for tracking the topic changes related to deep learning techniques on Stack Exchange and automatically interpreting each identified topic.
Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling
The coreference alignment modeling explicitly aligns coreferent mentions in conversation history with corresponding pronominal references in generated questions, which makes generated questions interconnected to conversation history.
Topic-Aware Neural Keyphrase Generation for Social Media Language
Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.
Doctor of Crosswise: Reducing Over-parametrization in Neural Networks
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks.
Microblog Hashtag Generation via Encoding Conversation Contexts
Automatic hashtag annotation plays an important role in content understanding for microblog posts.
HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition
In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured.
Information Aggregation for Multi-Head Attention with Routing-by-Agreement
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces.
What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations.
DDFlow: Learning Optical Flow with Unlabeled Data Distillation
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data.
Tools and Benchmarks for Automated Log Parsing
Logs are imperative in the development and maintenance process of many software systems.
Software Engineering
Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs
In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0, 1]$.
Multi-Head Attention with Disagreement Regularization
Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions.
Topic Memory Networks for Short Text Classification
Many classification models work poorly on short texts due to data sparsity.
Generating Distractors for Reading Comprehension Questions from Real Examinations
We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations.
Title-Guided Encoding for Keyphrase Generation
Keyphrase generation (KG) aims to generate a set of keyphrases given a document, which is a fundamental task in natural language processing (NLP).
Difficulty Controllable Generation of Reading Comprehension Questions
We investigate the difficulty levels of questions in reading comprehension datasets such as SQuAD, and propose a new question generation setting, named Difficulty-controllable Question Generation (DQG).
DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation
Our obfuscation approach is very effective to protect the critical structure of a deep learning model from being exposed to attackers.
Cryptography and Security
A Directed Acyclic Graph Approach to Online Log Parsing
A typical log-based system reliability management procedure is to first parse log messages because of their unstructured format; and apply data mining techniques on the parsed logs to obtain critical system behavior information.
Software Engineering
Code Completion with Neural Attention and Pointer Networks
Intelligent code completion has become an essential research task to accelerate modern software development.
Semantically Consistent Image Completion with Fine-grained Details
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs).
High-Resolution Deep Convolutional Generative Adversarial Networks
Generative Adversarial Networks (GANs) convergence in a high-resolution setting with a computational constrain of GPU memory capacity (from 12GB to 24 GB) has been beset with difficulty due to the known lack of convergence rate stability.
Ranked #1 on
Image Generation
on CelebA 128x128
(MS-SSIM metric)
On Secure and Usable Program Obfuscation: A Survey
On the other hand, the performance requirement for model-oriented obfuscation approaches is too weak to develop practical program obfuscation solutions.
Cryptography and Security Software Engineering
Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
Estimating covariance matrices is a fundamental technique in various domains, most notably in machine learning and signal processing.
A Survey of Point-of-interest Recommendation in Location-based Social Networks
Then, we present a comprehensive review in three aspects: influential factors for POI recommendation, methodologies employed for POI recommendation, and different tasks in POI recommendation.
N-Version Obfuscation: Impeding Software Tampering Replication with Program Diversity
Our idea is to impede the replication of tampering via program diversification, and thus increasing the complexity to break the whole software system.
Cryptography and Security Programming Languages
Combinatorial Pure Exploration of Multi-Armed Bandits
We also establish a general problem-dependent lower bound for the CPE problem.
Exact and Stable Recovery of Pairwise Interaction Tensors
For the noisy cases, we also prove error bounds for a constrained convex program for recovering the tensors.
