arXiv subjects

Jingjing Li

Publications and source records attributed to Jingjing Li.

At least 73 records · Page 4Linked to original sources

arXiv2025

Generative Artificial Intelligence-Guided User Studies: An Application for Air Taxi Services

User studies are crucial for meeting user needs. In user studies, real experimental scenarios and participants are constructed and recruited. However, emerging and unfamiliar studies face limitations, including safety concerns and iterative efficiency. To address these challenges, this study utilises a Generative Artificial Intelligence (GenAI) to create GenAI-generated scenarios for user experience (UX). By recruiting real users to evaluate this experience, we can collect feedback that enables rapid iteration in the early design phase. The air taxi is particularly representative of these challenges and has been chosen as the case study for this research. The key contribution was designing an Air Taxi Journey (ATJ) using Large Language Models (LLMs) and AI image and video generators. Based on the GPT-4-generated scripts, key visuals were created for the air taxi, and the ATJ was evaluated by 72 participants. Furthermore, the LLMs demonstrated the ability to identify and suggest environments that significantly improve participants' willingness toward air taxis. Education level and gender significantly influenced participants' the difference in willingness and their satisfaction with the ATJ. Satisfaction with the ATJ serves as a mediator, significantly influencing participants' willingness to take air taxis. Our study confirms the capability of GenAI to support user studies, providing a feasible approach and valuable insights for designing air taxi UX in the early design phase.

cs.HC↗

arXiv2025

Entropy-Based Decoding for Retrieval-Augmented Large Language Models

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and internal knowledge sources. In this paper, we introduce a novel, training-free decoding method guided by entropy considerations to mitigate this issue. Our approach utilizes entropy-based document-parallel ensemble decoding to prioritize low-entropy distributions from retrieved documents, thereby enhancing the extraction of relevant information of context. Additionally, it incorporates a contrastive decoding mechanism that contrasts the obtained low-entropy ensemble distribution with the high-entropy distribution derived from the model's internal knowledge across layers, which ensures a greater emphasis on reliable external information. Extensive experiments on open-domain question answering datasets demonstrate the superiority of our method.

cs.CL↗

arXiv2024

Entire-Space Variational Information Exploitation for Post-Click Conversion Rate Prediction

In recommender systems, post-click conversion rate (CVR) estimation is an essential task to model user preferences for items and estimate the value of recommendations. Sample selection bias (SSB) and data sparsity (DS) are two persistent challenges for post-click conversion rate (CVR) estimation. Currently, entire-space approaches that exploit unclicked samples through knowledge distillation are promising to mitigate SSB and DS simultaneously. Existing methods use non-conversion, conversion, or adaptive conversion predictors to generate pseudo labels for unclicked samples. However, they fail to consider the unbiasedness and information limitations of these pseudo labels. Motivated by such analysis, we propose an entire-space variational information exploitation framework (EVI) for CVR prediction. First, EVI uses a conditional entire-space CVR teacher to generate unbiased pseudo labels. Then, it applies variational information exploitation and logit distillation to transfer non-click space information to the target CVR estimator. We conduct extensive offline experiments on six large-scale datasets. EVI demonstrated a 2.25\% average improvement compared to the state-of-the-art baselines.

cs.IR↗

arXiv2024

CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models

Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese. However, the evaluation of these models remains underdeveloped due to a lack of benchmarks. To address this gap, we present CLongEval, a comprehensive Chinese benchmark for evaluating long-context LLMs. CLongEval is characterized by three key features: (1) Sufficient data volume, comprising 7 distinct tasks and 7,267 examples; (2) Broad applicability, accommodating to models with context windows size from 1K to 100K; (3) High quality, with over 2,000 manually annotated question-answer pairs in addition to the automatically constructed labels. With CLongEval, we undertake a comprehensive assessment of 6 open-source long-context LLMs and 2 leading commercial counterparts that feature both long-context abilities and proficiency in Chinese. We also provide in-depth analysis based on the empirical results, trying to shed light on the critical capabilities that present challenges in long-context settings. The dataset, evaluation scripts, and model outputs are released.

cs.CL↗

arXiv2024

SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation

Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries, resulting in sub-optimal performance. To address these limitations, we propose a novel plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm. By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG. We further enhance retrieval performance by fine-tuning LLMs with Proximal Policy Optimization (PPO) objectives using the trajectories collected by SeRTS as feedback. Controlled experiments using the BioASQ-QA dataset with GPT-3.5-Turbo and LLama2-7b demonstrate that our method significantly improves the performance of the BM25 retriever and surpasses the strong baseline of self-reflection in both efficiency and scalability. Moreover, SeRTS generates higher-quality feedback for PPO training than self-reflection. Our proposed method effectively adapts LLMs to document retrieval tasks, enhancing their ability to retrieve highly relevant documents for RAG in the context of medical knowledge queries. This work presents a significant step forward in leveraging LLMs for accurate and comprehensive biomedical question answering.

cs.CL↗

arXiv2024

Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions

With the exponential surge in diverse multi-modal data, traditional uni-modal retrieval methods struggle to meet the needs of users seeking access to data across various modalities. To address this, cross-modal retrieval has emerged, enabling interaction across modalities, facilitating semantic matching, and leveraging complementarity and consistency between heterogeneous data. Although prior literature has reviewed the field of cross-modal retrieval, it suffers from numerous deficiencies in terms of timeliness, taxonomy, and comprehensiveness. This paper conducts a comprehensive review of cross-modal retrieval's evolution, spanning from shallow statistical analysis techniques to vision-language pre-training models. Commencing with a comprehensive taxonomy grounded in machine learning paradigms, mechanisms, and models, the paper delves deeply into the principles and architectures underpinning existing cross-modal retrieval methods. Furthermore, it offers an overview of widely-used benchmarks, metrics, and performances. Lastly, the paper probes the prospects and challenges that confront contemporary cross-modal retrieval, while engaging in a discourse on potential directions for further progress in the field. To facilitate the ongoing research on cross-modal retrieval, we develop a user-friendly toolbox and an open-source repository at https://cross-modal-retrieval.github.io.

cs.IR↗

arXiv2024

TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models

Time series anomaly detection (TSAD) has gained significant attention due to its real-world applications to improve the stability of modern software systems. However, there is no effective way to verify whether they can meet the requirements for real-world deployment. Firstly, current algorithms typically train a specific model for each time series. Maintaining such many models is impractical in a large-scale system with tens of thousands of curves. The performance of using merely one unified model to detect anomalies remains unknown. Secondly, most TSAD models are trained on the historical part of a time series and are tested on its future segment. In distributed systems, however, there are frequent system deployments and upgrades, with new, previously unseen time series emerging daily. The performance of testing newly incoming unseen time series on current TSAD algorithms remains unknown. Lastly, the assumptions of the evaluation metrics in existing benchmarks are far from practical demands. To solve the above-mentioned problems, we propose an industrial-grade benchmark TimeSeriesBench. We assess the performance of existing algorithms across more than 168 evaluation settings and provide comprehensive analysis for the future design of anomaly detection algorithms. An industrial dataset is also released along with TimeSeriesBench.

cs.LG↗

arXiv2024

A Survey of Text Watermarking in the Era of Large Language Models

Text watermarking algorithms are crucial for protecting the copyright of textual content. Historically, their capabilities and application scenarios were limited. However, recent advancements in large language models (LLMs) have revolutionized these techniques. LLMs not only enhance text watermarking algorithms with their advanced abilities but also create a need for employing these algorithms to protect their own copyrights or prevent potential misuse. This paper conducts a comprehensive survey of the current state of text watermarking technology, covering four main aspects: (1) an overview and comparison of different text watermarking techniques; (2) evaluation methods for text watermarking algorithms, including their detectability, impact on text or LLM quality, robustness under target or untargeted attacks; (3) potential application scenarios for text watermarking technology; (4) current challenges and future directions for text watermarking. This survey aims to provide researchers with a thorough understanding of text watermarking technology in the era of LLM, thereby promoting its further advancement.

cs.CL↗

arXiv2024

An Entropy-based Text Watermarking Detection Method

Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most high-entropy scenarios, its performance in low-entropy scenarios still needs to be improved. In this work, we opine that the influence of token entropy should be fully considered in the watermark detection process, $i.e.$, the weight of each token during watermark detection should be customized according to its entropy, rather than setting the weights of all tokens to the same value as in previous methods. Specifically, we propose \textbf{E}ntropy-based Text \textbf{W}atermarking \textbf{D}etection (\textbf{EWD}) that gives higher-entropy tokens higher influence weights during watermark detection, so as to better reflect the degree of watermarking. Furthermore, the proposed detection process is training-free and fully automated. From the experiments, we demonstrate that our EWD can achieve better detection performance in low-entropy scenarios, and our method is also general and can be applied to texts with different entropy distributions. Our code and data is available\footnote{\url{https://github.com/luyijian3/EWD}}. Additionally, our algorithm could be accessed through MarkLLM \cite{pan2024markllm}\footnote{\url{https://github.com/THU-BPM/MarkLLM}}.

cs.CL↗

arXiv2024

VLBI with SKA: Possible Arrays and Astrometric Science

The next generation of very long baseline interferometry (VLBI) is stepping into the era of microarcsecond ($μ$as) astronomy, and pushing astronomy, especially astrometry, to new heights. VLBI with the Square Kilometre Array (SKA), SKA-VLBI, will increase current sensitivity by an order of magnitude, and reach astrometric precision routinely below 10 $μ$as, even challenging 1 $μ$as. This advancement allows precise parallax and proper motion measurements of various celestial objects. Such improvements can be used to study objects (including isolated objects, and binary or multiple systems) in different stellar stages (such as star formation, main-sequence stars, asymptotic giant branch stars, pulsars, black holes, white dwarfs, etc.), unveil the structure and evolution of complex systems (such as the Milky Way), benchmark the international celestial reference frame, and reveal cosmic expansion. Furthermore, the theory of general relativity can also be tested with SKA-VLBI using precise measurements of light deflection under the gravitational fields of different solar system objects and the perihelion precession of solar system objects.

astro-ph.GA↗

arXiv2024

How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO

The role-play ability of Large Language Models (LLMs) has emerged as a popular research direction. However, existing studies focus on imitating well-known public figures or fictional characters, overlooking the potential for simulating ordinary individuals. Such an oversight limits the potential for advancements in digital human clones and non-player characters in video games. To bridge this gap, we introduce ECHO, an evaluative framework inspired by the Turing test. This framework engages the acquaintances of the target individuals to distinguish between human and machine-generated responses. Notably, our framework focuses on emulating average individuals rather than historical or fictional figures, presenting a unique advantage to apply the Turing Test. We evaluated three role-playing LLMs using ECHO, with GPT-3.5 and GPT-4 serving as foundational models, alongside the online application GPTs from OpenAI. Our results demonstrate that GPT-4 more effectively deceives human evaluators, and GPTs achieves a leading success rate of 48.3%. Furthermore, we investigated whether LLMs could discern between human-generated and machine-generated texts. While GPT-4 can identify differences, it could not determine which texts were human-produced. Our code and results of reproducing the role-playing LLMs are made publicly available via https://github.com/CUHK-ARISE/ECHO.

cs.CL↗

arXiv2024

MaterialsMap: A CALPHAD-Based Tool to Design Composition Pathways through feasibility map for Desired Dissimilar Materials, demonstrated with RSW Joining of Ag-Al-Cu

Assembly of dissimilar metals can be achieved by different methods, for example, casting, welding, and additive manufacturing (AM). However, undesired phases formed in liquid-phase assembling processes due to solute segregation during solidification diminish mechanical and other properties of the processed parts. In the present work, an open-source software named MaterialsMap, has been developed based on the CALculation of Phase Diagrams (CALPHAD) approach. The primary objective of MaterialsMap is to facilitate the design of an optimal composition pathway for assembling dissimilar alloys with liquid-phases based on the formation of desired and undesired phases along the pathway. In MaterialsMap, equilibrium thermodynamic calculations are used to predict equilibrium phases formed at slow cooling rate, while Scheil-Gulliver simulations are employed to predict non-equilibrium phases formed during rapid cooling. By combining these two simulations, MaterialsMap offers a thorough guide for understanding phase formation in various manufacturing processes, assisting users in making informed decisions during material selection and production. As a demonstration of this approach, a compositional pathway was designed from pure Al to pure Cu through Ag using MaterialsMap. The design was experimentally verified using resistance spot welding (RSW).

cond-mat.mtrl-sci↗

arXiv2024

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://github.com/TL-UESTC/UniMoS

cs.CV↗

arXiv2024

Agile Multi-Source-Free Domain Adaptation

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.

cs.CV↗

arXiv2024

Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation

Conventional Unsupervised Domain Adaptation (UDA) strives to minimize distribution discrepancy between domains, which neglects to harness rich semantics from data and struggles to handle complex domain shifts. A promising technique is to leverage the knowledge of large-scale pre-trained vision-language models for more guided adaptation. Despite some endeavors, current methods often learn textual prompts to embed domain semantics for source and target domains separately and perform classification within each domain, limiting cross-domain knowledge transfer. Moreover, prompting only the language branch lacks flexibility to adapt both modalities dynamically. To bridge this gap, we propose Domain-Agnostic Mutual Prompting (DAMP) to exploit domain-invariant semantics by mutually aligning visual and textual embeddings. Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way. Meanwhile, visual prompts are imposed based on the domain-agnostic textual prompt to elicit domain-invariant visual embeddings. These two branches of prompts are learned mutually with a cross-attention module and regularized with a semantic-consistency loss and an instance-discrimination contrastive loss. Experiments on three UDA benchmarks demonstrate the superiority of DAMP over state-of-the-art approaches.

cs.AI↗

arXiv2024

Molecular Bubble and Outflow in S Mon Revealed by Multiband Datasets

We identify a molecular bubble, and study the star formation and its feedback in the S Mon region, using multiple molecular lines, young stellar objects (YSOs), and infrared data. We revisit the distance to S Mon, ~722+/-9 pc, using Gaia Data Release 3 parallaxes of the associated Class II YSOs. The bubble may be mainly driven by a massive binary system (namely 15 Mon), the primary of which is an O7V-type star. An outflow is detected in the shell of the bubble, suggesting ongoing star formation activities in the vicinity of the bubble. The total wind energy of the massive binary star is three orders of magnitude higher than the sum of the observed turbulent energy in the molecular gas and the kinetic energy of the bubble, indicating that stellar winds help to maintain the turbulence in the S Mon region and drive the bubble. We conclude that the stellar winds of massive stars have an impact on their surrounding environment.

astro-ph.GA↗

arXiv2023

Maser Investigation toward Off-Plane Stars (MIOPS): detection of SiO masers in the Galactic thick disk and halo

Studying stars that are located off the Galactic plane is important for understanding the formation history of the Milky Way. We searched for SiO masers toward off-plane O-rich asymptotic giant branch (AGB) stars from the catalog presented by Mauron et al. (2019) in order to shed light on the origin of these objects. A total of 102 stars were observed in the SiO $J$=1-0, $v=1$ and 2 transitions with the Effelsberg-100 m and Tianma-65 m telescopes. SiO masers were discovered in eight stars, all first detections. The measured maser velocities allow the first estimates of the host AGB stars' radial velocities. We find that the radial velocities of three stars (namely G068.881-24.615, G070.384-24.886, and G084.453-21.863) significantly deviate from the values expected from Galactic circular motion. The updated distances and 3D motions indicate that G068.881$-$24.615 is likely located in the Galactic halo, while G160.648-08.846 is probably located in the Galactic thin disk, and the other six stars are probably part of the Galactic thick disk.

astro-ph.GA↗

arXiv2023

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency regularization are commonly adopted to make the model less sensitive to domain-specific attributes. Consistency regularization enforces the model to output the same representation or prediction for two views of one image. These constraints, however, are either too strict or not order-preserving for the classification probabilities. In this work, we propose the Order-preserving Consistency Regularization (OCR) for cross-domain tasks. The order-preserving property for the prediction makes the model robust to task-irrelevant transformations. As a result, the model becomes less sensitive to the domain-specific attributes. The comprehensive experiments show that our method achieves clear advantages on five different cross-domain tasks.

cs.CV↗