Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting

While previous research in multivariate time series forecasting has focused on developing complex holistic models, this work advocates for a shift toward a granular, component-level understanding of their impacts. We propose TSCOMP, the first large-scale benchmark that systematically deconstructs deep forecasting methods into their core, fine-grained components--spanning series preprocessing, encoding strategies, network architectures including specific and large time-series models, and optimization methods. Using constrained orthogonal experimental design and extensive evaluations, we conduct multi-view analyses that reveal component effectiveness across different backbones, data characteristics, and their interactions. Beyond providing insights, this benchmark establishes a fine-grained performance corpus comprising over 20,000 model-dataset evaluations, which supports the learning of automated component selection, enabling zero-shot model construction on new datasets. Our experiments demonstrate that the corpus-driven approach, despite its simplicity, consistently outperforms state-of-the-art methods, validating the soundness of our evaluation design and confirming that systematic component selection surpasses manually designed complex architectures. All code and the performance corpus are publicly available at https://github.com/SUFE-AILAB/TSCOMP.

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark

Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address unique challenges or share fundamental mechanics. This paper introduces WSADBench, the first benchmark that unifies evaluation across distinct weakly supervised scenarios, benchmarking diverse approaches from specialized WSAD methods to advanced tabular foundation models. WSADBench establishes standardized protocols to evaluate 36 algorithms across 4 modalities by systematically varying label quantity, granularity, and quality, revealing the performance boundaries of various methods. Based on over 700K experiments, WSADBench reveals four critical insights: (i) Strong intrinsic correlations exist between these weak supervision scenarios, challenging the isolation of current research directions. (ii) Specialized WSAD algorithms excel only in extreme label-scarcity regimes but are quickly dominated by tabular foundation models and general classification methods as supervision increases or in OOD scenarios. (iii) Unlabeled data shows inconsistent utility across settings, with marginal gains compared to label refinement. (iv) Models exhibit asymmetric sensitivity to different types of label noise. We release WSADBench as an open-source benchmark with code and datasets to facilitate future WSAD research: https://github.com/SUFE-AILAB/WSADBench.

Automatic Robustness Stress Testing of LLMs as Mathematical Problem Solvers

Large language models (LLMs) have achieved distinguished performance on various reasoning-intensive tasks. However, LLMs might still face the challenges of robustness issues and fail unexpectedly in some simple reasoning tasks. Previous works evaluate the LLM robustness with hand-crafted templates or a limited set of perturbation rules, indicating potential data contamination in pre-training or fine-tuning datasets. In this work, inspired by stress testing in software engineering, we propose a novel framework, Automatic Robustness Checker (AR-Checker), to generate mathematical problem variants that maintain the semantic meanings of the original one but might fail the LLMs. The AR-Checker framework generates mathematical problem variants through multi-round parallel streams of LLM-based rewriting and verification. Our framework can generate benchmark variants dynamically for each LLM, thus minimizing the risk of data contamination. Experiments on GSM8K and MATH-500 demonstrate the strong performance of AR-Checker on mathematical tasks. We also evaluate AR-Checker on benchmarks beyond mathematics, including MMLU, MMLU-Pro, and CommonsenseQA, where it also achieves strong performance, further proving the effectiveness of AR-Checker.

SoP: Unlock the Power of Social Facilitation for Automatic Jailbreak Attack

The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse. Although aligned with human preference data before release, LLMs remain vulnerable to various malicious attacks. In this paper, we adopt a red-teaming strategy to enhance LLM safety and introduce SoP, a simple yet effective framework to design jailbreak prompts automatically. Inspired by the social facilitation concept, SoP generates and optimizes multiple jailbreak characters to bypass the guardrails of the target LLM. Different from previous work which relies on proprietary LLMs or seed jailbreak templates crafted by human expertise, SoP can generate and optimize the jailbreak prompt in a cold-start scenario using open-sourced LLMs without any seed jailbreak templates. Experimental results show that SoP achieves attack success rates of 88% and 60% in bypassing the safety alignment of GPT-3.5-1106 and GPT-4, respectively. Furthermore, we extensively evaluate the transferability of the generated templates across different LLMs and held-out malicious requests, while also exploring defense strategies against the jailbreak attack designed by SoP. Code is available at https://github.com/Yang-Yan-Yang-Yan/SoP.

Sample Design Engineering: An Empirical Study of What Makes Good Downstream Fine-Tuning Samples for LLMs

In the burgeoning field of Large Language Models (LLMs) like ChatGPT and LLaMA, Prompt Engineering (PE) is renowned for boosting zero-shot or in-context learning (ICL) through prompt modifications. Yet, the realm of the sample design for downstream fine-tuning, crucial for task-specific LLM adaptation, is largely unexplored. This paper introduces Sample Design Engineering (SDE), a methodical approach to enhancing LLMs' post-tuning performance by refining input, output, and reasoning designs. We conduct a series of in-domain (ID) and out-of-domain (OOD) experiments to assess the impact of various design options on LLMs' downstream performance, revealing several intriguing patterns that hold consistently across different LLMs. Based on these insights, we propose an integrated SDE strategy, combining the most effective options, and validate its consistent superiority over heuristic sample designs in complex downstream tasks like multi-aspect sentiment analysis, event extraction, and nested entity recognition. Additionally, analyses of LLMs' inherent prompt/output perplexity, zero-shot, and ICL abilities illustrate that good PE strategies may not always translate to good SDE strategies. Code available at https://github.com/beyondguo/LLM-Tuning.

Enhancing Molecular Property Prediction via Mixture of Collaborative Experts

Molecular Property Prediction (MPP) task involves predicting biochemical properties based on molecular features, such as molecular graph structures, contributing to the discovery of lead compounds in drug development. To address data scarcity and imbalance in MPP, some studies have adopted Graph Neural Networks (GNN) as an encoder to extract commonalities from molecular graphs. However, these approaches often use a separate predictor for each task, neglecting the shared characteristics among predictors corresponding to different tasks. In response to this limitation, we introduce the GNN-MoCE architecture. It employs the Mixture of Collaborative Experts (MoCE) as predictors, exploiting task commonalities while confronting the homogeneity issue in the expert pool and the decision dominance dilemma within the expert group. To enhance expert diversity for collaboration among all experts, the Expert-Specific Projection method is proposed to assign a unique projection perspective to each expert. To balance decision-making influence for collaboration within the expert group, the Expert-Specific Loss is presented to integrate individual expert loss into the weighted decision loss of the group for more equitable training. Benefiting from the enhancements of MoCE in expert creation, dynamic expert group formation, and experts' collaboration, our model demonstrates superior performance over traditional methods on 24 MPP datasets, especially in tasks with limited data or high imbalance.

ADGym: Design Choices for Deep Anomaly Detection

Deep learning (DL) techniques have recently been applied to anomaly detection (AD), yielding successful outcomes in areas such as finance, medical services, and cloud computing. However, much of the current research evaluates a deep AD algorithm holistically, failing to understand the contributions of individual design choices like loss functions and network architectures. Consequently, the importance of prerequisite steps, such as preprocessing, might be overshadowed by the spotlight on novel loss functions and architectures. In this paper, we address these oversights by posing two questions: (i) Which components (i.e., design choices) of deep AD methods are pivotal in detecting anomalies? (ii) How can we construct tailored AD algorithms for specific datasets by selecting the best design choices automatically, rather than relying on generic, pre-existing solutions? To this end, we introduce ADGym, the first platform designed for comprehensive evaluation and automatic selection of AD design elements in deep methods. Extensive experiments reveal that merely adopting existing leading methods is not ideal. Models crafted using ADGym markedly surpass current state-of-the-art techniques.

Anomaly Detection with Score Distribution Discrimination

Recent studies give more attention to the anomaly detection (AD) methods that can leverage a handful of labeled anomalies along with abundant unlabeled data. These existing anomaly-informed AD methods rely on manually predefined score target(s), e.g., prior constant or margin hyperparameter(s), to realize discrimination in anomaly scores between normal and abnormal data. However, such methods would be vulnerable to the existence of anomaly contamination in the unlabeled data, and also lack adaptation to different data scenarios. In this paper, we propose to optimize the anomaly scoring function from the view of score distribution, thus better retaining the diversity and more fine-grained information of input data, especially when the unlabeled data contains anomaly noises in more practical AD scenarios. We design a novel loss function called Overlap loss that minimizes the overlap area between the score distributions of normal and abnormal samples, which no longer depends on prior anomaly score targets and thus acquires adaptability to various datasets. Overlap loss consists of Score Distribution Estimator and Overlap Area Calculation, which are introduced to overcome challenges when estimating arbitrary score distributions, and to ensure the boundness of training loss. As a general loss component, Overlap loss can be effectively integrated into multiple network architectures for constructing AD models. Extensive experimental results indicate that Overlap loss based AD models significantly outperform their state-of-the-art counterparts, and achieve better performance on different types of anomalies.

Weakly Supervised Anomaly Detection: A Survey

Anomaly detection (AD) is a crucial task in machine learning with various applications, such as detecting emerging diseases, identifying financial frauds, and detecting fake news. However, obtaining complete, accurate, and precise labels for AD tasks can be expensive and challenging due to the cost and difficulties in data annotation. To address this issue, researchers have developed AD methods that can work with incomplete, inexact, and inaccurate supervision, collectively summarized as weakly supervised anomaly detection (WSAD) methods. In this study, we present the first comprehensive survey of WSAD methods by categorizing them into the above three weak supervision settings across four data modalities (i.e., tabular, graph, time-series, and image/video data). For each setting, we provide formal definitions, key algorithms, and potential future directions. To support future research, we conduct experiments on a selected setting and release the source code, along with a collection of WSAD methods and data.

GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation

We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens). GENIUS is pre-trained on a large-scale textual corpus with a novel reconstruction from sketch objective using an extreme and selective masking strategy, enabling it to generate diverse and high-quality texts given sketches. Comparison with other competitive conditional language models (CLMs) reveals the superiority of GENIUS's text generation quality. We further show that GENIUS can be used as a strong and ready-to-use data augmentation tool for various natural language processing (NLP) tasks. Most existing textual data augmentation methods are either too conservative, by making small changes to the original text, or too aggressive, by creating entirely new samples. With GENIUS, we propose GeniusAug, which first extracts the target-aware sketches from the original training set and then generates new samples based on the sketches. Empirical experiments on 6 text classification datasets show that GeniusAug significantly improves the models' performance in both in-distribution (ID) and out-of-distribution (OOD) settings. We also demonstrate the effectiveness of GeniusAug on named entity recognition (NER) and machine reading comprehension (MRC) tasks. (Code and models are publicly available at https://github.com/microsoft/SCGLab and https://github.com/beyondguo/genius)