Search

The rapid spread of rumors on social media platforms during breaking events severely hinders the dissemination of the truth. Previous studies reveal that the lack of annotated resources hinders the direct detection of unforeseen breaking events not covered in yesterday's news. Leveraging large language models (LLMs) for rumor detection holds significant promise. However, it is challenging for LLMs to provide comprehensive responses to complex or controversial issues due to limited diversity. In this work, we propose the Stance Separated Multi-Agent Debate (S2MAD) to address this issue. Specifically, we firstly introduce Stance Separation, categorizing comments as either supporting or opposing the original claim. Subsequently, claims are classified as subjective or objective, enabling agents to generate reasonable initial viewpoints with different prompt strategies for each type of claim. Debaters then follow specific instructions through multiple rounds of debate to reach a consensus. If a consensus is not reached, a judge agent evaluates the opinions and delivers a final verdict on the claim's veracity. Extensive experiments conducted on two real-world datasets demonstrate that our proposed model outperforms state-of-the-art methods in terms of performance and effectively improves the performance of LLMs in breaking event rumor detection.

In a relativistic framework, it is generally accepted that quantum steering of maximally entangled states provide greater advantages in practical applications compared to non-maximally entangled states. In this paper, we investigate quantum steering for four different types of Bell-like states of fermionic modes near the event horizon of a Schwarzschild black hole. In some parameter spaces, the peak of steering asymmetry corresponds to a transition from two-way to one-way steerability for Bell-like states under the influence of the Hawking effect. It is intriguing to find that the fermionic steerability of the maximally entangled states experiences sudden death with the Hawking temperature, while the fermionic steerability of the non-maximally entangled states maintains indefinite persistence at infinite Hawking temperature. In contrast to prior research, this finding suggests that quantum steering of non-maximally entangled states is more advantageous than that of maximally entangled states for processing quantum tasks in the gravitational background. This surprising result overturns the traditional idea of ``the advantage of maximally entangled steering in the relativistic framework" and provides a new perspective for understanding the Hawking effect of the black hole., Comment: 17 pages, 2 figures

With the advancement of large language models (LLMs), researchers have explored various methods to optimally leverage their comprehension and generation capabilities in sequential recommendation scenarios. However, several challenges persist in this endeavor. Firstly, most existing approaches rely on the input-output prompting paradigm, which can result in irrelevant or inaccurate responses. Secondly, while there have been attempts to enhance LLMs using prompting strategies such as chain-of-thought (CoT), these efforts have not fully harnessed the reasoning abilities of LLMs or effectively captured the multifaceted information contained within user sequences. To address these limitations, we propose GOT4Rec, a sequential recommendation method that utilizes the graph of thoughts (GoT) prompting strategy. Specifically, we identify and utilize three key types of information within user history sequences: short-term interests, long-term interests and collaborative information from other users. Our approach enables LLMs to independently reason and generate recommendations based on these distinct types of information, subsequently aggregating the results within the GoT framework to derive the final recommended items. This method allows LLMs, with enhanced reasoning capabilities, to more effectively consider the diverse information within user sequences, resulting in more accurate recommendations and more comprehensive explanations. Extensive experiments on real-world datasets demonstrate the effectiveness of GOT4Rec, indicating that it outperforms existing state-of-the-art baselines. Our code is available at https://anonymous.4open.science/r/GOT4Rec-ED99.

The advent of large language models (LLMs) has spurred the development of numerous jailbreak techniques aimed at circumventing their security defenses against malicious attacks. An effective jailbreak approach is to identify a domain where safety generalization fails, a phenomenon known as mismatched generalization. In this paper, we introduce two novel jailbreak methods based on mismatched generalization: natural language games and custom language games, both of which effectively bypass the safety mechanisms of LLMs, with various kinds and different variants, making them hard to defend and leading to high attack rates. Natural language games involve the use of synthetic linguistic constructs and the actions intertwined with these constructs, such as the Ubbi Dubbi language. Building on this phenomenon, we propose the custom language games method: by engaging with LLMs using a variety of custom rules, we successfully execute jailbreak attacks across multiple LLM platforms. Extensive experiments demonstrate the effectiveness of our methods, achieving success rates of 93% on GPT-4o, 89% on GPT-4o-mini and 83% on Claude-3.5-Sonnet. Furthermore, to investigate the generalizability of safety alignments, we fine-tuned Llama-3.1-70B with the custom language games to achieve safety alignment within our datasets and found that when interacting through other language games, the fine-tuned models still failed to identify harmful content. This finding indicates that the safety alignment knowledge embedded in LLMs fails to generalize across different linguistic formats, thus opening new avenues for future research in this area.

Next point-of-interest (POI) recommendation aims to predict a user's next destination based on sequential check-in history and a set of POI candidates. Graph neural networks (GNNs) have demonstrated a remarkable capability in this endeavor by exploiting the extensive global collaborative signals present among POIs. However, most of the existing graph-based approaches construct graph structures based on pre-defined heuristics, failing to consider inherent hierarchical structures of POI features such as geographical locations and visiting peaks, or suffering from noisy and incomplete structures in graphs. To address the aforementioned issues, this paper presents a novel Bi-level Graph Structure Learning (BiGSL) for next POI recommendation. BiGSL first learns a hierarchical graph structure to capture the fine-to-coarse connectivity between POIs and prototypes, and then uses a pairwise learning module to dynamically infer relationships between POI pairs and prototype pairs. Based on the learned bi-level graphs, our model then employs a multi-relational graph network that considers both POI- and prototype-level neighbors, resulting in improved POI representations. Our bi-level structure learning scheme is more robust to data noise and incompleteness, and improves the exploration ability for recommendation by alleviating sparsity issues. Experimental results on three real-world datasets demonstrate the superiority of our model over existing state-of-the-art methods, with a significant improvement in recommendation accuracy and exploration performance., Comment: Accepted by IEEE Transactions on Knowledge and Data Engineering

Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training and molecular context information. Despite these advancements, existing methods struggle with the ineffective fine-tuning of pre-trained encoders. We attribute this issue to the imbalance between the abundance of tunable parameters and the scarcity of labeled molecules, and the lack of contextual perceptiveness in the encoders. To overcome this hurdle, we propose a parameter-efficient in-context tuning method, named Pin-Tuning. Specifically, we propose a lightweight adapter for pre-trained message passing layers (MP-Adapter) and Bayesian weight consolidation for pre-trained atom/bond embedding layers (Emb-BWC), to achieve parameter-efficient tuning while preventing over-fitting and catastrophic forgetting. Additionally, we enhance the MP-Adapters with contextual perceptiveness. This innovation allows for in-context tuning of the pre-trained encoder, thereby improving its adaptability for specific FSMPP tasks. When evaluated on public datasets, our method demonstrates superior tuning with fewer trainable parameters, improving few-shot predictive performance., Comment: Accepted by NeurIPS 2024

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically assesses and enhances the quality of image-text pairs. AITQE employs a text rewriting mechanism for low-quality pairs and incorporates a negative sample learning strategy to improve evaluative capabilities by integrating deliberately selected low-quality samples during training. Unlike prior approaches that significantly alter text distributions, our method minimally adjusts text to preserve data volume while enhancing quality. Experimental results demonstrate that AITQE surpasses existing methods on various benchmark, effectively leveraging raw data and scaling efficiently with increasing data volumes. We hope our work will inspire future works. The code and model are available at: https://github.com/hanhuang22/AITQE.

It is generally believed that quantum entanglement in the maximally entangled states is greater than quantum entanglement in the non-maximally entangled states under a relativistic setting. In this paper, we study quantum entanglement for four different types of Bell-like states of the fermionic modes near the event horizon of a Schwarzschild black hole. It is interesting to find that quantum entanglement in the maximally entangled states is less than quantum entanglement in the non-maximally entangled states in Schwarzschild spacetime. From the perspective of quantum resources, the non-maximally entangled states may have more advantages in curved spacetime compared to the maximally entangled states. This is obviously different from the conclusions in previous paper. For two types of Bell-like states, quantum entanglement suffers sudden death under the Hawking effect of the black hole, and for the other two types of Bell-like states, quantum entanglement can exist forever regardless of the Hawking temperature. Therefore, we should choose appropriate types of Bell-like states to handle relativistic quantum information tasks.

Realizing large-scale quantum networks requires the generation of high-fidelity quantum entanglement states between remote quantum nodes, a key resource for quantum communication, distributed computation and sensing applications. However, entanglement distribution between quantum network nodes is hindered by optical transmission loss and local operation errors. Here, we propose a novel quantum repeater architecture that synergistically integrates Rydberg atom quantum processors with optical cavities to overcome these challenges. Our scheme leverages cavity-mediated interactions for efficient remote entanglement generation, followed by Rydberg interaction-based entanglement purification and swapping. Numerical simulations, incorporating realistic experimental parameters, demonstrate the generation of Bell states with 99\% fidelity at rates of 1.1\,kHz between two nodes in local-area network (distance $0.1\,\mathrm{km}$), and can be extend to metropolitan-area ($25\,\mathrm{km}$) or intercity ($\mathrm{250\,\mathrm{km}}$, with the assitance of frequency converters) network with a rate of 0.1\,kHz. This scalable approach opens up near-term opportunities for exploring quantum network applications and investigating the advantages of distributed quantum information processing., Comment: 3 figures

Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods often struggle with complex tasks, such as multi-hop reasoning. In this paper, we identify and investigate the phenomenon of Editing Overfit, where edited models assign disproportionately high probabilities to the edit target, hindering the generalization of new knowledge in complex scenarios. We attribute this issue to the current editing paradigm, which places excessive emphasis on the direct correspondence between the input prompt and the edit target for each edit sample. To further explore this issue, we introduce a new benchmark, EVOKE (EValuation of Editing Overfit in Knowledge Editing), along with fine-grained evaluation metrics. Through comprehensive experiments and analysis, we demonstrate that Editing Overfit is prevalent in current editing methods and that common overfitting mitigation strategies are of limited effectiveness in knowledge editing. To overcome this, inspired by LLMs' knowledge recall mechanisms, we propose a new plug-and-play strategy called Learn to Inference (LTI), which introduce a Multi-stage Inference Constraint module to guide the edited models in recalling new knowledge similarly to how unedited LLMs leverage knowledge through in-context learning. Extensive experimental results across a wide range of tasks validate the effectiveness of LTI in mitigating Editing Overfit.

In this article, we systematically discuss the decay patterns of the hidden-strange hadronic molecular state $N(2270)$ which is assumed as an S-wave $K^\ast\Sigma^\ast$ shallow bound state with its possible quantum numbers $J^P$ which are ${1/2}^-$, ${3/2}^-$ and ${5/2}^-$. By using the effective Lagrangian approach and considering pseudo-scalar meson and vector meson exchanges, we have thoroughly calculated and discussed the decay behavior of the $N(2270)$ molecular state, including hadronic and radiative decay and the cutoff dependence, for different $J^P$ values. For all three cases, $K^\ast \Lambda$, $K^\ast \Sigma$, and $\rho N$ final states are always included as the main decay channels. However, the $K \Lambda$, $\pi N$ and $\pi \Delta$ final states exhibit notable differences. These different decay properties will provide valuable guidance for future experimental searches and aid in distinguishing different $J^P$ assumptions and understanding their internal structures., Comment: 10 pages, 7 figures, 5 tables

With the emergence of various molecular tasks and massive datasets, how to perform efficient training has become an urgent yet under-explored issue in the area. Data pruning (DP), as an oft-stated approach to saving training burdens, filters out less influential samples to form a coreset for training. However, the increasing reliance on pretrained models for molecular tasks renders traditional in-domain DP methods incompatible. Therefore, we propose a Molecular data Pruning framework for enhanced Generalization (MolPeg), which focuses on the source-free data pruning scenario, where data pruning is applied with pretrained models. By maintaining two models with different updating paces during training, we introduce a novel scoring function to measure the informativeness of samples based on the loss discrepancy. As a plug-and-play framework, MolPeg realizes the perception of both source and target domain and consistently outperforms existing DP methods across four downstream tasks. Remarkably, it can surpass the performance obtained from full-dataset training, even when pruning up to 60-70% of the data on HIV and PCBA dataset. Our work suggests that the discovery of effective data-pruning metrics could provide a viable path to both enhanced efficiency and superior generalization in transfer learning., Comment: 20 pages, under review

Addressing critical challenges in Lamb wave resonators, this paper presents the first validation of resonators incorporating sub-wavelength through-holes. Using the A3 mode resonator based on a LiNbO3 single-crystal thin film and operating in the K band as a prominent example, we demonstrate the advantages of the through-hole design. In the absence of additional processing steps, and while maintaining device performance--including operating frequency, electromechanical coupling coefficient, and quality factor--without introducing extra spurious modes, this approach effectively reduces the ineffective suspension area of the piezoelectric LN film, potentially enhancing mechanical and thermal stability. It also standardizes etching distances (and times) across various Lamb wave resonators on a single wafer, facilitating the development of Lamb wave filters. The versatility of the through-hole technique, with relaxed constraints on hole geometry and arrangement, further highlights its significance. Together with the other advantages, these features underscore the transformative potential of through-holes in advancing the practical implementation of Lamb wave resonators and filters., Comment: 9 pages, 10 figures

Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing techniques exhibit promising performance in single-hop reasoning tasks, they show limitations when applied to multi-hop reasoning. Drawing on cognitive neuroscience and the operational mechanisms of LLMs, we hypothesize that the residual single-hop knowledge after editing causes edited models to revert to their original answers when processing multi-hop questions, thereby undermining their performance in multihop reasoning tasks. To validate this hypothesis, we conduct a series of experiments that empirically confirm our assumptions. Building on the validated hypothesis, we propose a novel knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE). Specifically, we design an erasure function for residual knowledge and an injection function for new knowledge. Through joint optimization, we derive the optimal recall vector, which is subsequently utilized within a rank-one editing framework to update the parameters of targeted model layers. Extensive experiments on GPT-J and GPT-2 XL demonstrate that KELE substantially enhances the multi-hop reasoning capability of edited LLMs.

We investigate asymmetric steering harvesting phenomenon involving two non-identical inertial detectors with different energy gaps, which interact locally with vacuum massless scalar fields. Our study assumes that the energy gap of detector $B$ exceeds that of detector $A$. It is shown that $A\rightarrow B$ steerability is bigger that $B\rightarrow A$ steerability, implying that the observer with a small energy gap has more stronger steerability than the other one. We find that the energy gap difference can enlarge the harvesting-achievable range of $A\rightarrow B$ steering, while it can also narrow the harvesting-achievable range of $B\rightarrow A$ steering at the same time. In addition, the maximal steering asymmetry indicates the transformation between two-way steering and one-way steering in some cases, showing that $B\rightarrow A$ steering suffers ``sudden death" at the point of this parameter. These results suggest that asymmetric steering exhibits richer and more interesting properties than quantum entanglement harvested from vacuum quantum field., Comment: 15 pages, 3 figures

This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions. Traditional graph learning algorithms, based on the assumption of uniform distribution between training and test data, falter in real-world scenarios where this assumption fails, resulting in suboptimal performance. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks trained through Stochastic Gradient Descent (SGD), which prefer simpler features over more complex yet equally or more predictive ones. This bias leads to a reliance on spurious correlations, adversely affecting OOD performance in various tasks such as image recognition, natural language understanding, and graph classification. Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, we propose DIVE, training a collection of models to focus on all label-predictive subgraphs by encouraging the models to foster divergence on the subgraph mask, which circumvents the limitation of a model solely focusing on the subgraph corresponding to simple structural patterns. Specifically, we employs a regularizer to punish overlap in extracted subgraphs across models, thereby encouraging different models to concentrate on distinct structural patterns. Model selection for robust OOD performance is achieved through validation accuracy. Tested across four datasets from GOOD benchmark and one dataset from DrugOOD benchmark, our approach demonstrates significant improvement over existing methods, effectively addressing the simplicity bias and enhancing generalization in graph machine learning.

Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more comprehensive information and lead to superior performance. However, the integration of multiple modalities often encounters the modal imbalance problem: since the information in different modalities is unbalanced, optimizing the same objective across all modalities leads to the under-optimization problem of the weak modalities with a slower convergence rate or lower performance. Even worse, we find that in multimodal recommendation models, all modalities suffer from the problem of insufficient optimization. To address these issues, we propose a Counterfactual Knowledge Distillation method that could solve the imbalance problem and make the best use of all modalities. Through modality-specific knowledge distillation, it could guide the multimodal model to learn modality-specific knowledge from uni-modal teachers. We also design a novel generic-and-specific distillation loss to guide the multimodal student to learn wider-and-deeper knowledge from teachers. Additionally, to adaptively recalibrate the focus of the multimodal model towards weaker modalities during training, we estimate the causal effect of each modality on the training objective using counterfactual inference techniques, through which we could determine the weak modalities, quantify the imbalance degree and re-weight the distillation loss accordingly. Our method could serve as a plug-and-play module for both late-fusion and early-fusion backbones. Extensive experiments on six backbones show that our proposed method can improve the performance by a large margin. The source code will be released at \url{https://github.com/CRIPAC-DIG/Balanced-Multimodal-Rec}, Comment: ACM Multimedia 2024 (Oral)

Claim verification is a task that involves assessing the truthfulness of a given claim based on multiple evidence pieces. Using large language models (LLMs) for claim verification is a promising way. However, simply feeding all the evidence pieces to an LLM and asking if the claim is factual does not yield good results. The challenge lies in the noisy nature of both the evidence and the claim: evidence passages typically contain irrelevant information, with the key facts hidden within the context, while claims often convey multiple aspects simultaneously. To navigate this "noisy crowd" of information, we propose EACon (Evidence Abstraction and Claim Deconstruction), a framework designed to find key information within evidence and verify each aspect of a claim separately. EACon first finds keywords from the claim and employs fuzzy matching to select relevant keywords for each raw evidence piece. These keywords serve as a guide to extract and summarize critical information into abstracted evidence. Subsequently, EACon deconstructs the original claim into subclaims, which are then verified against both abstracted and raw evidence individually. We evaluate EACon using two open-source LLMs on two challenging datasets. Results demonstrate that EACon consistently and substantially improve LLMs' performance in claim verification.

We study the N-partite coherences of GHZ and W states for free bosonic and fermionic fields when any n observers hover near the event horizon of a Garfinkle-Horowitz-Strominger (GHS) dilaton black hole. We derive the more general analytical expressions for N-partite coherence, encompassing both physically accessible and inaccessible coherences in the context of the dilaton black hole. It has been found that the coherence of the bosonic field is greater than that of the fermionic field, while the entanglement of the fermionic field is greater than that of the bosonic field in dilaton spacetime. Additionally, the coherence of the W state is greater than that of the GHZ state, whereas the entanglement of the GHZ state is greater than that of the W state in curved spacetime. These results suggest that we should utilize suitable quantum resources and different types of particles for relativistic quantum information tasks., Comment: 23 pages, 5 figures

Out-of-context news is a common type of misinformation on online media platforms. This involves posting a caption, alongside a mismatched news image. Existing out-of-context news detection models only consider the scenario where pre-labeled data is available for each domain, failing to address the out-of-context news detection on unlabeled domains (e.g. news topics or agencies). In this work, we therefore focus on domain adaptive out-of-context news detection. In order to effectively adapt the detection model to unlabeled news topics or agencies, we propose ConDA-TTA (Contrastive Domain Adaptation with Test-Time Adaptation) which applies contrastive learning and maximum mean discrepancy (MMD) to learn domain-invariant features. In addition, we leverage test-time target domain statistics to further assist domain adaptation. Experimental results show that our approach outperforms baselines in most domain adaptation settings on two public datasets, by as much as 2.93% in F1 and 2.08% in accuracy.

The rapid spread of information through mobile devices and media has led to the widespread of false or deceptive news, causing significant concerns in society. Among different types of misinformation, image repurposing, also known as out-of-context misinformation, remains highly prevalent and effective. However, current approaches for detecting out-of-context misinformation often lack interpretability and offer limited explanations. In this study, we propose a logic regularization approach for out-of-context detection called LOGRAN (LOGic Regularization for out-of-context ANalysis). The primary objective of LOGRAN is to decompose the out-of-context detection at the phrase level. By employing latent variables for phrase-level predictions, the final prediction of the image-caption pair can be aggregated using logical rules. The latent variables also provide an explanation for how the final result is derived, making this fine-grained detection method inherently explanatory. We evaluate the performance of LOGRAN on the NewsCLIPpings dataset, showcasing competitive overall results. Visualized examples also reveal faithful phrase-level predictions of out-of-context images, accompanied by explanations. This highlights the effectiveness of our approach in addressing out-of-context detection and enhancing interpretability., Comment: ICASSP 2024 lecture paper

This work proposes a double-layer thin-film lithium niobate (LiNbO3) longitudinally excited shear wave resonator with a theoretical electromechanical coupling coefficient exceeding 60%, RaR close to 28%, and no spurious modes. This ultra-large electromechanical coupling coefficient, which is close to the upper limit of LiNbO3, is much larger than all microwave acoustic resonators reported so far. Based on X-cut thin-film LiNbO3, when the film thickness is in the order of hundreds of nanometers, the frequency of the fundamental mode of the resonator can cover 1GHz to10GHz. The resonator design is convenient and flexible. The resonant frequency can be modulated monotonically by changing either the electrode or the thickness of the thin-film LiNbO3 without introducing additional spurious modes. This ideal resonator architecture is also applicable to LiTaO3. With the development of the new generation of mobile communications, this resonator is expected to become a key solution for future high-performance, ultra-wide-bandwidth acoustic filters., Comment: 15 pages,9 figures

Starting with the density field equation of a self-gravity fluid in a static Universe, using the Schwinger functional differentiation technique, we derive the field equation of the 4-point correlation function (4PCF) of galaxies in the Gaussian approximation, which contains hierarchically 2PCF and 3PCF. By use of the known solutions of 2PCF and 3PCF, the equation of 4PCF becomes an inhomogeneous, Helmholtz equation, and contains only two physical parameters: the mass $m$ of galaxy and the Jeans wavenumber $k_J$, like the equations of the 2PCF and 3PCF. We obtain the analytical solution of 4PCF that consists of four portions, $\eta= \eta^0_{odd} + \eta^0_{even} +\eta^{FP} +\eta^I$, and has a very rich structure. $\eta^0_{odd}$ and $\eta^0_{even}$ form the homogeneous solution and depend on boundary conditions. The parity-odd $\eta^0_{odd}$ is more interesting and qualitatively explains the observed parity-odd data of BOSS CMASS, the parity-even $\eta^0_{even}$ contains the disconnected 4PCF $\eta^{disc}$ (arising from a Gaussian random process), and both $\eta^0_{odd}$ and $\eta^0_{even}$ are prominent at large scales $r\gtrsim 10$Mpc, and exhibit radial oscillations determined by the Jeans wavenumber. $\eta^{FP}$ and $ \eta^I$ are parity-even, and form the inhomogeneous solution. $\eta^{FP}$ is the same as the Fry-Peebles ansatz for 4PCF, and dominates at small scales $r \lesssim 10$Mpc. $\eta^I$ is an integration of the inhomogeneous term, subdominant. We also compare the parity-even 4PCF with the observation data., Comment: 31 pages, 9 figures

We study quantum steering and Bell nonlocality harvested by the local interaction of two Unruh-DeWitt detectors with the vacuum massless scalar field, both in the presence of gravitational waves and in Minkowski spacetime. It is shown that quantum steerability under the influence of gravitational waves can be greater than or less than quantum steerability in Minkowski spacetime, which means that the gravitational waves can amplify or degrade the harvested steering. In particular, a resonance effect occurs when the energy gap of the detector is tuned to the frequency of the gravitational wave. We also find that the harvesting-achievable separation range of vacuum steering can be expanded or reduced by the presence of gravitational waves, which depends on the energy gap, the gravitational wave frequency, and the duration of the gravitational wave action. It is interesting to note that two detector systems that satisfy the Bell inequality in most parameter spaces, regardless of the existence of gravitational waves, indicating that steering harvesting cannot be considered to be nonlocal., Comment: 19 pages, 3 figures

With the continuous accumulation of data from hadron collision experiments, efficient Partial Wave Analysis tools are indispensable for constructing a clear hadron spectrum. Currently, automated computations of scattering amplitudes primarily use the helicity scheme and covariant effective Lagrangian method. The automated calculations under the covariant $L$-$S$ scheme, which is one of the commonly used partial wave analysis schemes, have not been fully realized. In this work, we provide a general algorithm for computing partial wave amplitudes under the covariant $L$-$S$ scheme. This will lay the foundation for automated computation of partial wave amplitudes under the covariant $L$-$S$ scheme., Comment: 6 pages

Due to the rapid spread of rumors on social media, rumor detection has become an extremely important challenge. Recently, numerous rumor detection models which utilize textual information and the propagation structure of events have been proposed. However, these methods overlook the importance of semantic evolvement information of event in propagation process, which is often challenging to be truly learned in supervised training paradigms and traditional rumor detection methods. To address this issue, we propose a novel semantic evolvement enhanced Graph Autoencoder for Rumor Detection (GARD) model in this paper. The model learns semantic evolvement information of events by capturing local semantic changes and global semantic evolvement information through specific graph autoencoder and reconstruction strategies. By combining semantic evolvement information and propagation structure information, the model achieves a comprehensive understanding of event propagation and perform accurate and robust detection, while also detecting rumors earlier by capturing semantic evolvement information in the early stages. Moreover, in order to enhance the model's ability to learn the distinct patterns of rumors and non-rumors, we introduce a uniformity regularizer to further improve the model's performance. Experimental results on three public benchmark datasets confirm the superiority of our GARD method over the state-of-the-art approaches in both overall performance and early rumor detection.

In this paper, we use the concepts of quantum entanglement and coherence to analyze the Unruh and anti-Unruh effects based on the model of Unruh-DeWitt detector. For the first time, we find that (i) the Unruh effect reduces quantum entanglement but enhances quantum coherence; (ii) the anti-Unruh effect enhances quantum entanglement but reduces quantum coherence. This surprising result refutes the notion that the Unruh effect can only destroy quantum entanglement and coherence simultaneously, and that the anti-Unruh can only protect quantum resources. Consequently, it opens up a new source for discovering experimental evidence supporting the existence of the Unruh and anti-Unruh effects., Comment: 12 pages, 2 figures

Due to the rapid spread of rumors on social media, rumor detection has become an extremely important challenge. Existing methods for rumor detection have achieved good performance, as they have collected enough corpus from the same data distribution for model training. However, significant distribution shifts between the training data and real-world test data occur due to differences in news topics, social media platforms, languages and the variance in propagation scale caused by news popularity. This leads to a substantial decline in the performance of these existing methods in Out-Of-Distribution (OOD) situations. To address this problem, we propose a simple and efficient method named Test-time Adaptation for Rumor Detection under distribution shifts (TARD). This method models the propagation of news in the form of a propagation graph, and builds propagation graph test-time adaptation framework, enhancing the model's adaptability and robustness when facing OOD problems. Extensive experiments conducted on two group datasets collected from real-world social platforms demonstrate that our framework outperforms the state-of-the-art methods in performance.

Complex quantum information tasks in a gravitational background require multipartite entanglement for effective processing. Therefore, it is necessary to investigate the properties of multipartite entanglement in a relativistic setting. In this paper, we study genuine N-partite entanglement of massless Dirac fields in the Schwarzschild-de Sitter (SdS) spacetime, characterized by the presence of a black hole event horizon (BEH) and a cosmological event horizon (CEH). We obtain the general analytical expression of genuine N-partite entanglement shared by $n$ observers near BEH and $m$ ($n+m=N$) observers near CEH. It is shown that genuine N-partite entanglement monotonically decreases with the decrease of the mass of the black hole, suggesting that the Hawking effect of the black hole destroys quantum entanglement. It is interesting to note that genuine N-partite entanglement is a non-monotonic function of the cosmological constant, meaning that the Hawking effect of the expanding universe can enhance quantum entanglement. This result contrasts with multipartite entanglement in single-event horizon spacetime, offering a new perspective on the Hawking effect in multi-event horizon spacetime., Comment: 18 pages, 4 figures

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to construct a new Large $\textbf{V}$ision-$\textbf{L}$anguage Model $\textbf{K}$nowledge $\textbf{E}$diting $\textbf{B}$enchmark, $\textbf{VLKEB}$, and extend the Portability metric for more comprehensive evaluation. Leveraging a multi-modal knowledge graph, our image data are bound with knowledge entities. This can be further used to extract entity-related knowledge, which constitutes the base of editing data. We conduct experiments of different editing methods on five LVLMs, and thoroughly analyze how do they impact the models. The results reveal strengths and deficiencies of these methods and hopefully provide insights for future research. The codes and dataset are available at: https://github.com/VLKEB/VLKEB., Comment: NeurIPS 2024, Datasets and Benchmarks Track

With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society. One of the unique challenges for fake news detection on social media is how to detect fake news on future events. Recently, numerous fake news detection models that utilize textual information and the propagation structure of posts have been proposed. Unfortunately, most of the existing approaches can hardly handle this challenge since they rely heavily on event-specific features for prediction and cannot generalize to unseen events. To address this, we introduce \textbf{F}uture \textbf{AD}aptive \textbf{E}vent-based Fake news Detection (FADE) framework. Specifically, we train a target predictor through an adaptive augmentation strategy and graph contrastive learning to obtain higher-quality features and make more accurate overall predictions. Simultaneously, we independently train an event-only predictor to obtain biased predictions. We further mitigate event bias by subtracting the event-only predictor's output from the target predictor's output to obtain the final prediction. Encouraging results from experiments designed to emulate real-world social media conditions validate the effectiveness of our method in comparison to existing state-of-the-art approaches.

We have experimentally investigated the mechanism of the exchange bias in the 2D van der Waals (vdW) ferromagnets by means of the anomalous Hall effect (AHE) together with the dynamical magnetization property. The temperature dependence of the AC susceptibility with its frequency response indicates a glassy transition of the magnetic property for the Te-rich FeGeTe vdW ferromagnet. We also found that the irreversible temperature dependence in the anomalous Hall voltage follows the Almeida-Thouless line. Moreover, the freezing temperature of the spin-glass-like phase is found to correlate with the disappearance temperature of the exchange bias. These important signatures suggest that the emergence of magnetic exchange bias in the 2D van der Waals ferromagnets is induced by the presence of the spin-glass-like state in FeGeTe. The unprecedented insights gained from these findings shed light on the underlying principles governing exchange bias in vdW ferromagnets, contributing to the advancement of our understanding in this field., Comment: 21 pages, 4 figures

Temporal Knowledge Graph (TKG) forecasting aims to predict future facts based on given histories. Most recent graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities. Nowadays, with the surge of LLMs, the LLM-based TKG prediction model has emerged. However, the existing LLM-based model exhibits three shortcomings: (1) It only focuses on the first-order history for prediction while ignoring high-order historical information, resulting in the provided information for LLMs being extremely limited. (2) LLMs struggle with optimal reasoning performance under heavy historical information loads. (3) For TKG prediction, the temporal reasoning capability of LLM alone is limited. To address the first two challenges, we propose Chain-of-History (CoH) reasoning which explores high-order histories step-by-step, achieving effective utilization of high-order historical information for LLMs on TKG prediction. To address the third issue, we design CoH as a plug-and-play module to enhance the performance of graph-based models for TKG prediction. Extensive experiments on three datasets and backbones demonstrate the effectiveness of CoH.

Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of postedit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge.

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods. TGM-DLM updates token embeddings within the SMILES string collectively and iteratively, using a two-phase diffusion generation process. The first phase optimizes embeddings from random noise, guided by the text description, while the second phase corrects invalid SMILES strings to form valid molecular representations. We demonstrate that TGM-DLM outperforms MolT5-Base, an autoregressive model, without the need for additional data resources. Our findings underscore the remarkable effectiveness of TGM-DLM in generating coherent and precise molecules with specific properties, opening new avenues in drug discovery and related scientific domains. Code will be released at: https://github.com/Deno-V/tgm-dlm., Comment: Accepted by 38th Association for the Advancement of Artificial Intelligence, AAAI

Fact checking aims to predict claim veracity by reasoning over multiple evidence pieces. It usually involves evidence retrieval and veracity reasoning. In this paper, we focus on the latter, reasoning over unstructured text and structured table information. Previous works have primarily relied on fine-tuning pretrained language models or training homogeneous-graph-based models. Despite their effectiveness, we argue that they fail to explore the rich semantic information underlying the evidence with different structures. To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC. Our approach leverages a heterogeneous evidence graph, with words as nodes and thoughtfully designed edges representing different evidence properties. We perform information propagation via a relational graph neural network, facilitating interactions between claims and evidence. An attention-based method is utilized to integrate information, combined with a language model for generating predictions. We introduce a multitask loss function to account for potential inaccuracies in evidence retrieval. Comprehensive experiments on the large fact checking dataset FEVEROUS demonstrate the effectiveness of HeterFC. Code will be released at: https://github.com/Deno-V/HeterFC., Comment: Accepted by 38th Association for the Advancement of Artificial Intelligence, AAAI

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely overlooked. In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual content during the testing phase, without requiring direct interference with the model's training process. Additionally, the attack is notably stealthy, as it does not affect the overall recommendation performance and the modifications to the text are subtle, making it difficult for users and platforms to detect. Our comprehensive experiments across four mainstream LLM-based recommendation models demonstrate the superior efficacy and stealthiness of our approach. Our work unveils a significant security gap in LLM-based recommendation systems and paves the way for future research on protecting these systems., Comment: ACL 2024 Main

Object hallucination has been an Achilles' heel which hinders the broader applications of large vision-language models (LVLMs). Object hallucination refers to the phenomenon that the LVLMs claim non-existent objects in the image. To mitigate the object hallucinations, instruction tuning and external model-based detection methods have been proposed, which either require large-scare computational resources or depend on the detection result of external models. However, there remains an under-explored field to utilize the LVLM itself to alleviate object hallucinations. In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects. Therefore, we propose a Logical Closed Loop-based framework for Object Hallucination Detection and Mitigation, namely LogicCheckGPT. In specific, we devise logical consistency probing to raise questions with logical correlations, inquiring about attributes from objects and vice versa. Whether their responses can form a logical closed loop serves as an indicator of object hallucination. As a plug-and-play method, it can be seamlessly applied to all existing LVLMs. Comprehensive experiments conducted on three benchmarks across four LVLMs have demonstrated significant improvements brought by our method, indicating its effectiveness and generality., Comment: Accept to ACL 2024; 19 Pages, 15 Figures, 6 Tables

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past few years, but the recent advent of graph masked autoencoder (GraphMAE) rekindles the momentum behind generative methods. Despite the empirical success of GraphMAE, there is still a dearth of theoretical understanding regarding its efficacy. Moreover, while both generative and contrastive methods have been shown to be effective, their connections and differences have yet to be thoroughly investigated. Therefore, we theoretically build a bridge between GraphMAE and GCL, and prove that the node-level reconstruction objective in GraphMAE implicitly performs context-level GCL. Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL. We point out that GraphMAE's alignment performance is restricted by the masking strategy, and the uniformity is not strictly guaranteed. To remedy the aforementioned limitations, we propose an Alignment-Uniformity enhanced Graph Masked AutoEncoder, named AUG-MAE. Specifically, we propose an easy-to-hard adversarial masking strategy to provide hard-to-align samples, which improves the alignment performance. Meanwhile, we introduce an explicit uniformity regularizer to ensure the uniformity of the learned representations. Experimental results on benchmark datasets demonstrate the superiority of our model over existing state-of-the-art methods., Comment: Accepted by AAAI 2024

In this work, we investigate to use Large Language Models (LLMs) for rumor detection on social media. However, it is challenging for LLMs to reason over the entire propagation information on social media, which contains news contents and numerous comments, due to LLMs may not concentrate on key clues in the complex propagation information, and have trouble in reasoning when facing massive and redundant information. Accordingly, we propose an LLM-empowered Rumor Detection (LeRuD) approach, in which we design prompts to teach LLMs to reason over important clues in news and comments, and divide the entire propagation information into a Chain-of-Propagation for reducing LLMs' burden. We conduct extensive experiments on the Twitter and Weibo datasets, and LeRuD outperforms several state-of-the-art rumor detection models by 3.2% to 7.7%. Meanwhile, by applying LLMs, LeRuD requires no data for training, and thus shows more promising rumor detection ability in few-shot or zero-shot scenarios.

The different spatial curvatures of the universe affect the measurement of cosmological distances, which may also contribute to explaining the observed dimming of type Ia supernovae. This phenomenon may be caused by the opacity of the universe. Similarly, the opacity of the universe can lead to a bias in our measurements of curvature. Thus, it is necessary to measure cosmic curvature and opacity simultaneously. In this paper, we propose a new model-independent method to simultaneously measure the cosmic curvature and opacity by using the latest observations of HII galaxies acting as standard candles and the latest Hubble parameter observations. The machine learning method-Artificial Neural Network is adopted to reconstruct observed Hubble parameter $H(z)$ observations. Our results support a slightly opaque and flat universe at $1\sigma$ confidence level by using previous 156 HII regions sample. However, the negative curvature is obtained by using the latest 181 HII regions sample in the redshift range $z\sim 2.5$. More importantly, we obtain the simultaneous measurements with precision on the cosmic opacity $\rm\Delta\tau\sim 10^{-2}$ and curvature $\rm\Delta\Omega_K\sim 10^{-1}$. A strong degeneracy between the cosmic opacity and curvature parameters is also revealed in this analysis., Comment: 11 pages, 5 figures