arXiv subjects

Yixin Liu

Publications and source records attributed to Yixin Liu.

At least 91 records · Page 5Linked to original sources

arXiv2024

ARC: A Generalist Graph Anomaly Detector with In-Context Learning

Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the majority within a graph, has garnered significant attention. However, current GAD methods necessitate training specific to each dataset, resulting in high training costs, substantial data requirements, and limited generalizability when being applied to new datasets and domains. To address these limitations, this paper proposes ARC, a generalist GAD approach that enables a ``one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly. Equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset using few-shot normal samples at the inference stage, without the need for retraining or fine-tuning on the target dataset. ARC comprises three components that are well-crafted for capturing universal graph anomaly patterns: 1) smoothness-based feature Alignment module that unifies the features of different datasets into a common and anomaly-sensitive space; 2) ego-neighbor Residual graph encoder that learns abnormality-related node embeddings; and 3) cross-attentive in-Context anomaly scoring module that predicts node abnormality by leveraging few-shot normal samples. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.

cs.LG↗

arXiv2024

Distributed Massive MIMO-Aided Task Offloading in Satellite-Terrestrial Integrated Multi-Tier VEC Networks

This paper proposes a distributed massive multiple input multiple-output (DM-MIMO) aided multi-tier vehicular edge computing (VEC) system. In particular, each vehicle terminal (VT) offloads its computational task to the roadside unit (RSU) by orthogonal frequency division multiple access (OFDMA), which can be computed locally at the RSU and offloaded to the central processing unit (CPU) via massive satellite access points (SAPs) for remote computation. By considering the partial task offloading model, we consider the joint optimization of the task offloading, subchannel allocation and precoding optimization to minimize the total cost in terms of total delay and energy consumption. To solve this non-convex problem, we transform the original problem into three sub-problems and use the alternate optimization algorithm to solve it. First, we transform the subcarrier allocation problem of discrete variables into convex optimization problem of continuous variables. Then, we use multiple quadratic transformations and Lagrange multiplier method to transform the non-convex subproblem of optimizing precoding vectors into a convex problem, while the task offloading subproblem is a convex problem. Given the subcarrier and the task allocation and precoding result, we finally find the joint optimized results by iterative optimization algorithm. Simulation results show that our proposed algorithm is superior to other benchmarks.

cs.DC↗

arXiv2024

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They primarily investigated how LLMs effectively collaborate with given specific tools. However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests. Therefore, in this paper, we introduce MetaTool, a benchmark designed to evaluate whether LLMs have tool usage awareness and can correctly choose tools. Specifically, we create a dataset called ToolE within the benchmark. This dataset contains various types of user queries in the form of prompts that trigger LLMs to use tools, including both single-tool and multi-tool scenarios. Subsequently, we set the tasks for both tool usage awareness and tool selection. We define four subtasks from different perspectives in tool selection, including tool selection with similar choices, tool selection in specific scenarios, tool selection with possible reliability issues, and multi-tool selection. We conduct experiments involving eight popular LLMs and find that the majority of them still struggle to effectively select tools, highlighting the existing gaps between LLMs and genuine intelligent agents. However, through the error analysis, we found there is still significant room for improvement. Finally, we conclude with insights for tool developers -- we strongly recommend that tool developers choose an appropriate rewrite model for generating new descriptions based on the downstream LLM the tool will apply to. Our code is in https://github.com/HowieHwong/MetaTool.

cs.SE↗

arXiv2024

M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models

Existing benchmarks for evaluating foundation models mainly focus on single-document, text-only tasks. However, they often fail to fully capture the complexity of research workflows, which typically involve interpreting non-textual data and gathering information across multiple documents. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3SciQA consists of 1,452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster represents a primary paper along with all its cited documents, mirroring the workflow of comprehending a single paper by requiring multi-modal and multi-document data. With M3SciQA, we conduct a comprehensive evaluation of 18 foundation models. Our results indicate that current foundation models still significantly underperform compared to human experts in multi-modal information retrieval and in reasoning across multiple scientific documents. Additionally, we explore the implications of these findings for the future advancement of applying foundation models in multi-modal scientific literature analysis.

cs.CL↗

arXiv2024

Calibrating Long-form Generations from Large Language Models

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods and calibration metrics typically rely on a binary true/false assessment of response correctness. This approach does not apply to long-form generation, where an answer can be partially correct. Addressing this gap, we introduce a unified calibration framework, in which both the correctness of the LLMs' responses and their associated confidence levels are treated as distributions across a range of scores. Within this framework, we develop three metrics to precisely evaluate LLM calibration and further propose two confidence elicitation methods based on self-consistency and self-evaluation. Our experiments, which include long-form QA and summarization tasks, demonstrate that larger models don't necessarily guarantee better calibration, that calibration performance is found to be metric-dependent, and that self-consistency methods excel in factoid datasets. We also find that calibration can be enhanced through techniques such as fine-tuning, integrating relevant source documents, scaling the temperature, and combining self-consistency with self-evaluation. Lastly, we showcase a practical application of our system: selecting and cascading open-source models and ChatGPT to optimize correctness given a limited API budget. This research not only challenges existing notions of LLM calibration but also offers practical methodologies for improving trustworthiness in long-form generation.

cs.CL↗

arXiv2024

FOLIO: Natural Language Reasoning with First-Order Logic

Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the complex logical reasoning capabilities of a model. We present FOLIO, a human-annotated, logically complex and diverse dataset for reasoning in natural language (NL), equipped with first-order logic (FOL) annotations. FOLIO consists of 1,430 examples (unique conclusions), each paired with one of 487 sets of premises used to deductively reason for the validity of each conclusion. The logical correctness of the premises and conclusions is ensured by their FOL annotations, which are automatically verified by an FOL inference engine. In addition to the main NL reasoning task, NL-FOL pairs in FOLIO constitute a new NL-FOL translation dataset. Our experiments on FOLIO systematically evaluate the FOL reasoning ability of supervised fine-tuning on medium-sized language models. For both NL reasoning and NL-FOL translation, we benchmark multiple state-of-the-art language models. Our results show that a subset of FOLIO presents a challenge for one of the most capable {Large Language Model (LLM)} publicly available, GPT-4.

cs.CL↗

arXiv2024

ReIFE: Re-evaluating Instruction-Following Evaluation

The automatic evaluation of instruction following typically involves using large language models (LLMs) to assess response quality. However, there is a lack of comprehensive evaluation of these LLM-based evaluators across two dimensions: the base LLMs and the evaluation protocols. Therefore, we present a thorough meta-evaluation of instruction following, including 25 base LLMs and 15 recently proposed evaluation protocols, on 4 human-annotated datasets, assessing the evaluation accuracy of the LLM-evaluators. Our evaluation allows us to identify the best-performing base LLMs and evaluation protocols with a high degree of robustness. Moreover, our large-scale evaluation reveals: (1) Base LLM performance ranking remains largely consistent across evaluation protocols, with less capable LLMs showing greater improvement from protocol enhancements; (2) Robust evaluation of evaluation protocols requires many base LLMs with varying capability levels, as protocol effectiveness can depend on the base LLM used; (3) Evaluation results on different datasets are not always consistent, so a rigorous evaluation requires multiple datasets with distinctive features. We release our meta-evaluation suite ReIFE, which provides the codebase and evaluation result collection for more than 500 LLM-evaluator configurations, to support future research in instruction-following evaluation.

cs.CL↗

arXiv2024

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI Sora remains challenging due to their closed-source nature. Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality. In this paper, we introduce Mora, a novel multi-agent framework that leverages existing open-source modules to replicate Sora functionalities. We address these fundamental limitations by proposing three key techniques: (1) multi-agent fine-tuning with a self-modulation factor to enhance inter-agent coordination, (2) a data-free training strategy that uses large models to synthesize training data, and (3) a human-in-the-loop mechanism combined with multimodal large language models for data filtering to ensure high-quality training datasets. Our comprehensive experiments on six video generation tasks demonstrate that Mora achieves performance comparable to Sora on VBench, outperforming existing open-source methods across various tasks. Specifically, in the text-to-video generation task, Mora achieved a Video Quality score of 0.800, surpassing Sora 0.797 and outperforming all other baseline models across six key metrics. Additionally, in the image-to-video generation task, Mora achieved a perfect Dynamic Degree score of 1.00, demonstrating exceptional capability in enhancing motion realism and achieving higher Imaging Quality than Sora. These results highlight the potential of collaborative multi-agent systems and human-in-the-loop mechanisms in advancing text-to-video generation. Our code is available at \url{https://github.com/lichao-sun/Mora}.

cs.CV↗

arXiv2024

The Unique Taste of LLMs for Papers: Potential issues in Using LLMs for Digital Library Document Recommendation Tasks

This paper investigates the performance of several representative large models in the field of literature recommendation and explores potential biases. The results indicate that while some large models' recommendations can be somewhat satisfactory after simple manual screening, overall, the accuracy of these models in specific literature recommendation tasks is generally moderate. Additionally, the models tend to recommend literature that is timely, collaborative, and expands or deepens the field. In scholar recommendation tasks. There is no evidence to suggest that LLMs exacerbate inequalities related to gender, race, or the level of development of countries.

cs.DL↗

arXiv2024

Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective

The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing these analyses through the lens of a data poisoning attack. By analyzing solvers' responses to such attacks, this work aims to contribute to the development of more robust linear solvers and provide insights into poisoning attacks on linear solvers. In particular, we investigate how the errors in the input data will affect the fitting error and accuracy of the solution from a linear system-solving algorithm under perturbations common in adversarial attacks. We propose data perturbation through two distinct knowledge levels, developing a poisoning optimization and studying two methods of perturbation: Label-guided Perturbation (LP) and Unconditioning Perturbation (UP). Existing works mainly focus on deriving the worst-case perturbation bound from a theoretical perspective, and the analysis is often limited to specific kinds of linear system solvers. Under the circumstance that the data is intentionally perturbed -- as is the case with data poisoning -- we seek to understand how different kinds of solvers react to these perturbations, identifying those algorithms most impacted by different types of adversarial attacks.

cs.LG↗

arXiv2024

TrustLLM: Trustworthiness in Large Language Models

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

cs.CL↗

arXiv2024

Unique quantum metallic state in the titanium sesquioxide heterointerface superconductor

The emergence of quantum metallic state marked by a saturating finite electrical resistance in the zero-temperature limit in a variety of two-dimensional superconductors injects an exciting momentum to the realm of heterostructure superconductivity. Despite much research efforts over last few decades, there is not yet a general consensus on the nature of this unexpected quantum metal. Here, we report the observation of a unique quantum metallic state within the hallmark of Bose-metal in the titanium sesquioxide heterointerface superconductor Ti$_2$O$_3$/GaN. Remarkably, the quantum bosonic metallic state continuously tuned by a magnetic field in the vicinity of the two-dimensional superconductivity-metal transition persists in the normal phase, indicating the existence of composite bosons formed by electron Cooper pairs even in the normal phase. Our findings provide a distinct evidence for electron pairing in the normal phase of heterointerface superconductors, and shed fresh light on the pairing nature underlying heterointerface superconductivity.

cond-mat.supr-con↗

arXiv2024

From weak to strong-coupling superconductivity tuned by substrate in TiN films

The interplay between substrates and superconducting thin films has attracted increasing attention. Here, we report an in-depth investigation on superconducting properties of the epitaxial TiN thin films grown on three different substrates by dc reactive magnetron sputtering. The TiN films grown on (0001) sapphire exhibit (111) crystal orientation, while that grown on (100) Si and MgO substrates exhibit (100) orientation. Moreover, the samples grown on Si reveal a relatively lower level of disorder, accompanied by the higher critical transition temperature $T_c$ and smaller magnitude of upper critical field slope near $T_c$. Remarkably, we uncovered a rather high value of superconducting gap (with $Δ_0/k_BT_c$ = 3.05) in TiN film on Si indicating a very strong coupling superconductivity, in sharp contrast to the case using sapphires and MgO as the substrate which reveals a weak-coupling feature. The comprehensive analysis considering the scenarios of the three substrate shows that the grain size of the thin films may be an important factor influencing the superconductivity.

cond-mat.supr-con↗

arXiv2024

Can Large Language Models Automatically Jailbreak GPT-4V?

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite researchers' efforts in safety alignment through RLHF or preprocessing filters, vulnerabilities might still be exploited. In our study, we introduce AutoJailbreak, an innovative automatic jailbreak technique inspired by prompt optimization. We leverage Large Language Models (LLMs) for red-teaming to refine the jailbreak prompt and employ weak-to-strong in-context learning prompts to boost efficiency. Furthermore, we present an effective search method that incorporates early stopping to minimize optimization time and token expenditure. Our experiments demonstrate that AutoJailbreak significantly surpasses conventional methods, achieving an Attack Success Rate (ASR) exceeding 95.3\%. This research sheds light on strengthening GPT-4V security, underscoring the potential for LLMs to be exploited in compromising GPT-4V integrity.

cs.CL↗

arXiv2024

Understanding Reference Policies in Direct Preference Optimization

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference model or policy. Such reference policies, typically instantiated as the model to be further fine-tuned, are important since they can impose an upper limit on DPO's effectiveness. Therefore, we address three related research questions in this work. First, we explore the optimal strength of the KL divergence constraint in DPO, which penalizes deviations from the reference policy, and find that DPO is sensitive to this strength. Next, we examine the necessity of the KL-constraint from the reference policies in DPO by providing both theoretical and empirical comparisons between DPO and related learning objectives, demonstrating DPO's superiority in this controlled setting. Additionally, we investigate whether DPO benefits from stronger reference policies, finding that a stronger reference policy can lead to improved performance, but only when it is similar to the model being fine-tuned. Our findings highlight the confounding role of reference policies in DPO and offer insights for best practices, while also identifying open research questions for future studies.

cs.CL↗

arXiv2024

BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency.

cs.CL↗

arXiv2024

DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents

Recent LLMs have demonstrated remarkable performance in solving exam-like math word problems. However, the degree to which these numerical reasoning skills are effective in real-world scenarios, particularly in expert domains, is still largely unexplored. This paper introduces DocMath-Eval, a comprehensive benchmark specifically designed to evaluate the numerical reasoning capabilities of LLMs in the context of understanding and analyzing specialized documents containing both text and tables. We conduct an extensive evaluation of 48 LLMs with Chain-of-Thought and Program-of-Thought prompting methods, aiming to comprehensively assess the capabilities and limitations of existing LLMs in DocMath-Eval. We found that even the current best-performing system (i.e., GPT-4o) still significantly lags behind human experts in solving complex numerical reasoning problems grounded in long contexts. We believe that DocMath-Eval can serve as a valuable benchmark for evaluating LLMs' capabilities in solving challenging numerical reasoning problems within expert domains.

cs.CL↗

arXiv2024

From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach

Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce. Existing efforts in graph anomaly detection typically only consider the information in a single scale (view), thus inevitably limiting their capability in capturing anomalous patterns in complex graph data. To address this limitation, we propose a novel framework, graph ANomaly dEtection framework with Multi-scale cONtrastive lEarning (ANEMONE in short). By using a graph neural network as a backbone to encode the information from multiple graph scales (views), we learn better representation for nodes in a graph. In maximizing the agreements between instances at both the patch and context levels concurrently, we estimate the anomaly score of each node with a statistical anomaly estimator according to the degree of agreement from multiple perspectives. To further exploit a handful of ground-truth anomalies (few-shot anomalies) that may be collected in real-life applications, we further propose an extended algorithm, ANEMONE-FS, to integrate valuable information in our method. We conduct extensive experiments under purely unsupervised settings and few-shot anomaly detection settings, and we demonstrate that the proposed method ANEMONE and its variant ANEMONE-FS consistently outperform state-of-the-art algorithms on six benchmark datasets.

cs.LG↗