Large language models (LLMs) are widely adopted in knowledge-intensive tasks and have achieved impressive performance thanks to their knowledge abilities. While LLMs have demonstrated outstanding performance on atomic or linear (multi-hop) QA tasks, whether they can reason in knowledge-rich scenarios with interweaving constraints remains an underexplored problem. In this work, we propose geometric reasoning over structured knowledge, where pieces of knowledge are connected in a graph structure and models need to fill in the missing information of this graph. Such geometric knowledge reasoning would require the ability to handle structured knowledge, reason with uncertainty, verify facts, and backtrack when an error occurs. Further analysis reveals that LLMs' ability of geometric reasoning over structured knowledge is still far from robust or perfect, susceptible to confounders such as the order of options, certain structural patterns, assumption of existence of correct answer, and more. Large language models (LLMs) have demonstrated an impressive ability on knowledge-intensive tasks such as open-domain QA (Petroni et al., 2019), misinformation detection (Karimi & Tang, 2019), and fact-checking (Gao et al., 2023). To assess the knowledge abilities of LLMs, existing tasks and datasets mostly focus on atomic (e.g., open-domain QA) (Rajpurkar et al., 2016; Das et al., 2022) or linear (e.g., multi-hop QA) (Press et al., 2022) settings, probing LLMs' responses to simple or multiple concatenated facts where each reasoning step has a unique definite answer. However, knowledge is not always arranged in a simple linear manner: it often involves more complex structural information, forming an interweaving network that connects various entities and relations through multiple chains as illustrated in Figure 1. Each reasoning step of atomic or linear QAs leads to a unique and definite (intermediate) answer, while multiple candidates exist before all constraints are jointly considered in geometric QA. Consequently, an underexplored yet crucial question arises: Can LLMs extend beyond linear compositionality and aggregate information from multiple chains along with various knowledge constraints? Specifically, when certain pieces of knowledge are missing, can LLMs successfully fill in the blanks based on existing constraints represented by other available information in the network? In this work, we evaluate how well models can aggregate information from the given constraints across a graph representing pieces of knowledge and figure out the blanks in this graph.

Large language models (LLMs) often encounter knowledge conflicts, scenarios where discrepancy arises between the internal parametric knowledge of LLMs and non-parametric information provided in the prompt context. In this work we ask what are the desiderata for LLMs when a knowledge conflict arises and whether existing LLMs fulfill them. We posit that LLMs should 1) identify knowledge conflicts, 2) pinpoint conflicting information segments, and 3) provide distinct answers or viewpoints in conflicting scenarios. To this end, we introduce KNOWLEDGE CONFLICT, an evaluation framework for simulating contextual knowledge conflicts and quantitatively evaluating to what extent LLMs achieve these goals. KNOWLEDGE CONFLICT includes diverse and complex situations of knowledge conflict, knowledge from diverse entities and domains, two synthetic conflict creation methods, and settings with progressively increasing difficulty to reflect realistic knowledge conflicts. Extensive experiments with the KNOWLEDGE CONFLICT framework reveal that while LLMs perform well in identifying the existence of knowledge conflicts, they struggle to determine the specific conflicting knowledge and produce a response with distinct answers amidst conflicting information. To address these challenges, we propose new instruction-based approaches that augment LLMs to better achieve the three goals. Further analysis shows that abilities to tackle knowledge conflicts are greatly impacted by factors such as knowledge domain and prompt text, while generating robust responses to knowledge conflict scenarios remains an open research question.

Language models (LMs) are pretrained on diverse data sources, including news, discussion forums, books, and online encyclopedias. A significant portion of this data includes opinions and perspectives which, on one hand, celebrate democracy and diversity of ideas, and on the other hand are inherently socially biased. Our work develops new methods to (1) measure political biases in LMs trained on such corpora, along social and economic axes, and (2) measure the fairness of downstream NLP models trained on top of politically biased LMs. We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks. Our findings reveal that pretrained LMs do have political leanings that reinforce the polarization present in pretraining corpora, propagating social biases into hate speech predictions and misinformation detectors. We discuss the implications of our findings for NLP research and propose future directions to mitigate unfairness.

With the advent of pretrained language models (LMs), increasing research efforts have been focusing on infusing commonsense and domain-specific knowledge to prepare LMs for downstream tasks. These works attempt to leverage knowledge graphs, the de facto standard of symbolic knowledge representation, along with pretrained LMs. While existing approaches have leveraged external knowledge, it remains an open question how to jointly incorporate knowledge graphs representing varying contexts, from local (e.g., sentence), to document-level, to global knowledge, to enable knowledge-rich exchange across these contexts. Such rich contextualization can be especially beneficial for long document understanding tasks since standard pretrained LMs are typically bounded by the input sequence length. In light of these challenges, we propose KALM, a Knowledge-Aware Language Model that jointly leverages knowledge in local, document-level, and global contexts for long document understanding. KALM first encodes long documents and knowledge graphs into the three knowledge-aware context representations. It then processes each context with context-specific layers, followed by a context fusion layer that facilitates knowledge exchange to derive an overarching document representation. Extensive experiments demonstrate that KALM achieves state-of-the-art performance on six long document understanding tasks and datasets. Further analyses reveal that the three knowledge-aware contexts are complementary and they all contribute to model performance, while the importance and information exchange patterns of different contexts vary with respect to different tasks and datasets.

Twitter bots are automatic programs operated by malicious actors to manipulate public opinion and spread misinformation. Research efforts have been made to automatically identify bots based on texts and networks on social media. Existing methods only leverage texts or networks alone, and while few works explored the shallow combination of the two modalities, we hypothesize that the interaction and information exchange between texts and graphs could be crucial for holistically evaluating bot activities on social media. In addition, according to a recent survey (Cresci, 2020), Twitter bots are constantly evolving while advanced bots steal genuine users' tweets and dilute their malicious content to evade detection. This results in greater inconsistency across the timeline of novel Twitter bots, which warrants more attention. In light of these challenges, we propose BIC, a Twitter Bot detection framework with text-graph Interaction and semantic Consistency. Specifically, in addition to separately modeling the two modalities on social media, BIC employs a text-graph interaction module to enable information exchange across modalities in the learning process. In addition, given the stealing behavior of novel Twitter bots, BIC proposes to model semantic consistency in tweets based on attention weights while using it to augment the decision process. Extensive experiments demonstrate that BIC consistently outperforms state-of-the-art baselines on two widely adopted datasets. Further analyses reveal that text-graph interactions and modeling semantic consistency are essential improvements and help combat bot evolution.

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion. Most existing KGE methods suffer from the sparsity challenge, where it is harder to predict entities that appear less frequently in knowledge graphs. In this work, we propose a novel framework KRACL to alleviate the widespread sparsity in KGs with graph context and contrastive learning. Firstly, we propose the Knowledge Relational Attention Network (KRAT) to leverage the graph context by simultaneously projecting neighboring triples to different latent spaces and jointly aggregating messages with the attention mechanism. KRAT is capable of capturing the subtle semantic information and importance of different context triples as well as leveraging multi-hop information in knowledge graphs. Secondly, we propose the knowledge contrastive loss by combining the contrastive loss with cross entropy loss, which introduces more negative samples and thus enriches the feedback to sparse entities. Our experiments demonstrate that KRACL achieves superior results across various standard knowledge graph benchmarks, especially on WN18RR and NELL-995 which have large numbers of low in-degree entities. Extensive experiments also bear out KRACL's effectiveness in handling sparse knowledge graphs and robustness against noisy triples.

Twitter bot detection has become an increasingly important task to combat misinformation, facilitate social media moderation, and preserve the integrity of the online discourse. State-of-the-art bot detection methods generally leverage the graph structure of the Twitter network, and they exhibit promising performance when confronting novel Twitter bots that traditional methods fail to detect. However, very few of the existing Twitter bot detection datasets are graph-based, and even these few graph-based datasets suffer from limited dataset scale, incomplete graph structure, as well as low annotation quality. In fact, the lack of a large-scale graph-based Twitter bot detection benchmark that addresses these issues has seriously hindered the development and evaluation of novel graph-based bot detection approaches. In this paper, we propose TwiBot-22, a comprehensive graph-based Twitter bot detection benchmark that presents the largest dataset to date, provides diversified entities and relations on the Twitter network, and has considerably better annotation quality than existing datasets. In addition, we re-implement 35 representative Twitter bot detection baselines and evaluate them on 9 datasets, including TwiBot-22, to promote a fair comparison of model performance and a holistic understanding of research progress. To facilitate further research, we consolidate all implemented codes and datasets into the TwiBot-22 evaluation framework, where researchers could consistently evaluate new models and datasets. The TwiBot-22 Twitter bot detection benchmark and evaluation framework are publicly available at https://twibot22.github.io/.

Graph convolutional networks (GCNs) have been widely adopted for graph representation learning and achieved impressive performance. For larger graphs stored separately on different clients, distributed GCN training algorithms were proposed to improve efficiency and scalability. However, existing methods directly exchange node features between different clients, which results in data privacy leakage. Federated learning was incorporated in graph learning to tackle data privacy, while they suffer from severe performance drop due to non-iid data distribution. Besides, these approaches generally involve heavy communication and memory overhead during the training process. In light of these problems, we propose a Privacy-Preserving Subgraph sampling based distributed GCN training method (PPSGCN), which preserves data privacy and significantly cuts back on communication and memory overhead. Specifically, PPSGCN employs a star-topology client-server system. We firstly sample a local node subset in each client to form a global subgraph, which greatly reduces communication and memory costs. We then conduct local computation on each client with features or gradients of the sampled nodes. Finally, all clients securely communicate with the central server with homomorphic encryption to combine local results while preserving data privacy. Compared with federated graph learning methods, our PPSGCN model is trained on a global graph to avoid the negative impact of local data distribution. We prove that our PPSGCN algorithm would converge to a local optimum with probability 1. Experiment results on three prevalent benchmarks demonstrate that our algorithm significantly reduces communication and memory overhead while maintaining desirable performance. Further studies not only demonstrate the fast convergence of PPSGCN, but discuss the trade-off between communication and local computation cost as well.

Identifying political perspective in news media has become an important task due to the rapid growth of political commentary and the increasingly polarized ideologies. Previous approaches only focus on leveraging the semantic information and leaves out the rich social and political context that helps individuals understand political stances. In this paper, we propose a perspective detection method that incorporates external knowledge of real-world politics. Specifically, we construct a contemporary political knowledge graph with 1,071 entities and 10,703 triples. We then build a heterogeneous information network for each news document that jointly models article semantics and external knowledge in knowledge graphs. Finally, we apply gated relational graph convolutional networks and conduct political perspective detection as graph-level classification. Extensive experiments show that our method achieves the best performance and outperforms state-of-the-art methods by 5.49\%. Numerous ablation studies further bear out the necessity of external knowledge and the effectiveness of our graph-based approach.

Political stance detection has become an important task due to the increasingly polarized political ideologies. Most existing works focus on identifying perspectives in news articles or social media posts, while social entities, such as individuals and organizations, produce these texts and actually take stances. In this paper, we propose the novel task of entity stance prediction, which aims to predict entities' stances given their social and political context. Specifically, we retrieve facts from Wikipedia about social entities regarding contemporary U.S. politics. We then annotate social entities' stances towards political ideologies with the help of domain experts. After defining the task of entity stance prediction, we propose a graph-based solution, which constructs a heterogeneous information network from collected facts and adopts gated relational graph convolutional networks for representation learning. Our model is then trained with a combination of supervised, self-supervised and unsupervised loss functions, which are motivated by multiple social and political phenomenons. We conduct extensive experiments to compare our method with existing text and graph analysis baselines. Our model achieves highest stance detection accuracy and yields inspiring insights regarding social entity stances. We further conduct ablation study and parameter analysis to study the mechanism and effectiveness of our proposed approach.