Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output is not only contextually relevant but also accurate and current. We introduce XRAG, an open-source, modular codebase that facilitates exhaustive evaluation of the performance of foundational components of advanced RAG modules. These components are systematically categorized into four core phases: pre-retrieval, retrieval, post-retrieval, and generation. We systematically analyse them across reconfigured datasets, providing a comprehensive benchmark for their effectiveness. As the complexity of RAG systems continues to escalate, we underscore the critical need to identify potential failure points in RAG systems. We formulate a suite of experimental methodologies and diagnostic testing protocols to dissect the failure points inherent in RAG engineering. Subsequently, we proffer bespoke solutions aimed at bolstering the overall performance of these modules. Our work thoroughly evaluates the performance of advanced core components in RAG systems, providing insights into optimizations for prevalent failure points.

Timeline summarization (TLS) system involves creating a concise overview of extended daily summaries through sentence and date selection, employing predefined unlearnable representations for these elements. This poses a unique challenge, as it involves normal representations that limit the performance of the downstream daily summarization tasks. Previous research in this field separately encoded dates and sentences in independent learning representation spaces, hindering the integration of their relationships and the attainment of a globally optimal summary by the TLS system. In this study, our emphasis is on pretraining a document encoder for the TLS system, where we introduce the concept of representing each document as a plug-and-play document plugin (PlugIN). Specifically, the proposed MegraTLS (Meta-graph autoencoder based TimeLine Summarization System) is based on a modified meta-graph autoencoder network. By incorporating the prefabricated PlugIN into the backbone of theDateWiseTLS framework for downstream timeline summarization, we streamline the encoding of a document, enabling efficient handling of date and sentence selection within a compact representation space in date and sentence embeddings. The experimental results demonstrate that our MegraTLS prominently promotes existing TLS frameworks in timeline summarization performance. Besides, the MegraTLS exhibits robustness and insensitivity to parameter changes. Case studies of financial events illustrate that our model accurately captures key timeline events when applied to specific fields, providing more industry-specific valuable information than ground truth while maintaining simplicity. Although our experiments are conducted exclusively on Chinese datasets, the methodological insights and empirical findings of this work offer transferable, actionable, and robust guidance for deploying timeline summarization technology in domain-specific industrial applications.

Autonomous driving has made significant progress in both academia and industry, including performance improvements in perception tasks and the development of end-to-end autonomous driving systems. However, the safety and robustness assessment of autonomous driving has not received sufficient attention. Current evaluations of autonomous driving are typically conducted in natural driving scenarios. However, accidents often occur in edge cases, also known as safety-critical scenarios. These safety-critical scenarios are difficult to collect, and there is currently no clear definition of what constitutes a safety-critical scenario. In this work, we explore the safety and robustness of autonomous driving in safety-critical scenarios. First, we provide a definition of safety-critical scenarios, including static traffic scenarios such as adversarial attack scenarios and natural distribution shifts, as well as dynamic traffic scenarios such as accident scenarios. Then, we develop an autonomous driving test framework to comprehensively evaluate autonomous driving systems, encompassing not only the assessment of perception modules but also system-level evaluations. Our work systematically constructs a safety verification process for autonomous driving, providing technical support for the industry to establish standardized test framework.

Multi-modal relation extraction (MMRE) is a challenging task that seeks to identify relationships between entities with textual and visual attributes. However, existing methods struggle to handle the complexities posed by multiple entity pairs within a single sentence that share similar contextual information (e.g., identical text and image content). These scenarios amplify the difficulty of distinguishing relationships and hinder accurate extraction. To address these limitations, we propose the variational multi-modal hypergraph attention network (VM-HAN), a novel and robust framework for MMRE. Unlike previous approaches, VM-HAN constructs a multi-modal hypergraph for each sentence-image pair, explicitly modeling high-order intra-/inter-modal correlations among different entity pairs in the same context. This design enables a more detailed and nuanced understanding of entity relationships by capturing intricate cross-modal interactions that are often overlooked. Additionally, we introduce the variational hypergraph attention network (V-HAN). This variational attention mechanism dynamically refines the hypergraph structure, enabling the model to effectively handle the inherent ambiguity and complexity of multi-modal data. Comprehensive experiments on benchmark MMRE datasets demonstrate that VM-HAN achieves state-of-the-art performance, significantly surpassing existing methods in both accuracy and efficiency.

Knowledge graph reasoning plays a vital role in various applications and has garnered considerable attention. Recently, path-based methods have achieved impressive performance. However, they may face limitations stemming from constraints in message-passing neural networks, such as missing paths and information over-squashing. In this paper, we revisit the application of transformers for knowledge graph reasoning to address the constraints faced by path-based methods and propose a novel method KnowFormer. KnowFormer utilizes a transformer architecture to perform reasoning on knowledge graphs from the message-passing perspective, rather than reasoning by textual information like previous pretrained language model based methods. Specifically, we define the attention computation based on the query prototype of knowledge graph reasoning, facilitating convenient construction and efficient optimization. To incorporate structural information into the self-attention mechanism, we introduce structure-aware modules to calculate query, key, and value respectively. Additionally, we present an efficient attention computation method for better scalability. Experimental results demonstrate the superior performance of KnowFormer compared to prominent baseline methods on both transductive and inductive benchmarks.

Reasoning complex logical queries on incomplete and massive knowledge graphs (KGs) remains a significant challenge. The prevailing method for this problem is query embedding, which embeds KG units (i.e., entities and relations) and complex queries into low-dimensional space. Recent developments in the field show that embedding queries as geometric shapes is a viable means for modeling entity set and logical relationships between them. Despite being promising, current geometric-based methods face challenges in capturing hierarchical structures of complex queries, which leaves considerable room for improvement. This paper presents POINE2, a geometric-based query embedding framework based on hyperbolic geometry to handle complex queries on knowledge graphs. POINE2 maps entities and queries as geometric shapes on a Cartesian product space of Poincaré ball spaces. To capture the hierarchical structures of complex queries, we use the Poincaré radius to represent the different levels of the hierarchy, and we use the aperture of the shape to indicate semantic differences at the same level of the hierarchy. Additionally, POINE2 offers a flexible and expressive definition of logical operations. Experimental results show that POINE2 outperforms existing salient geometric-based embedding methods and significantly improves these methods on evaluation datasets.

Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks.However, a significant challenge nowadays is maintaining performance when we use a lightweight model with limited labelled samples.We present DisCo, a semi-supervised learning (SSL) framework for fine-tuning a cohort of small student models generated from a large PLM using knowledge distillation.Our key insight is to share complementary knowledge among distilled student cohorts to promote their SSL effectiveness.DisCo employs a novel co-training technique to optimize a cohort of multiple small student models by promoting knowledge sharing among students under diversified views: model views produced by different distillation strategies and data views produced by various input augmentations.We evaluate DisCo on both semi-supervised text classification and extractive summarization tasks.Experimental results show that DisCo can produce student models that are 7.6× smaller and 4.8× faster in inference than the baseline PLMs while maintaining comparable performance.We also show that DisCo-generated student models outperform the similar-sized models elaborately tuned in distinct tasks.

We propose a neuralized undirected graphical model called Neural-Hidden-CRF to solve the weakly-supervised sequence labeling problem. Under the umbrella of undirected graphical theory, the proposed Neural-Hidden-CRF embedded with a hidden CRF layer models the variables of word sequence, latent ground truth sequence, and weak label sequence with the global perspective that undirected graphical models particularly enjoy. In Neural-Hidden-CRF, we can capitalize on the powerful language model BERT or other deep models to provide rich contextual semantic knowledge to the latent ground truth sequence, and use the hidden CRF layer to capture the internal label dependencies. Neural-Hidden-CRF is conceptually simple and empirically powerful. It obtains new state-of-the-art results on one crowdsourcing benchmark and three weak-supervision benchmarks, including outperforming the recent advanced model CHMM by 2.80 F1 points and 2.23 F1 points in average generalization and inference performance, respectively.

Labeling large amounts of extractive summarization data is often prohibitive expensive due to time, financial, and expertise constraints, which poses great challenges to incorporating summarization system in practical applications. This limitation can be overcome by semi-supervised approaches: consistency-training and pseudo-labeling to make full use of unlabeled data. Researches on the two, however, are conducted independently, and very few works try to connect them. In this paper, we first use the noise-injected consistency training paradigm to regularize model predictions. Subsequently, we propose a novel entropy-constrained pseudo labeling strategy to obtain high-confidence labels from unlabeled predictions, which can obtain high-confidence labels from unlabeled predictions by comparing the entropy of supervised and unsupervised predictions. By combining consistency training and pseudo-labeling, this framework enforce a low-density separation between classes, which decently improves the performance of supervised learning over an insufficient labeled extractive summarization dataset.

Timeline summarization (TLS) identifies major events and generates short summaries on how the event evolves in a period of time. Existing timeline summarization methods generate summaries by considering the coverage and diversity of the content and temporized information but ignore the importance and coherence of sentences used in summary. However, ignoring such information often causes missing important facts in the generated TLS and confuses users. We propose a better approach for TLS by explicitly optimizing importance and coherence on top of coverage and diversity. We apply our approach to both direct and pipeline TLS frameworks. Experimental results show that our approach achieves better performance when compared with two state-of-the-art TLS methods.

Fact-checking is vital for countering fake news. This process requires verifying the truthfulness of a claim by reasoning about multiple pieces of evidence. The current dominant approach depends upon capturing the claim-evidence relations from a claim-evidence interaction graph. Existing solutions utilize phrase-level semantics on a single-granularity but ignore other hierarchical features, such as fact- and sentence-level textual semantics and their logical topology. Since the hierarchical features often provide hints to infer collaborative high-order clues that can be essential for fact-checking, they should not be overlooked. This paper proposes a better method to model the claim-evidence graph in a multi-granularity manner. Doing so allows one to exploit more textual semantics and logical topology between a claim and its evidence. To achieve the target, we first employ a graph inference learning framework to infer graph nodes on different granular semantic units within their hierarchical topology. Then, an inference learning procedure is designed to optimize the global textual similarity and local topological reachability from the claim-evidence graph. We evaluate our approach by applying it to fact-checking on an open dataset, and experimental results show that our technique outperforms existing graph-based techniques by a large margin.

Recent studies of extractive text summarization have leveraged BERT for document encoding with breakthrough performance. However, when using a pre-trained BERT-based encoder, existing approaches for selecting representative sentences for text summarization are inadequate since the encoder is not explicitly trained for representing sentences. Simply providing the BERT-initialized sentences to cross-sentential graph-based neural networks (GNNs) to encode semantic features of the sentences is not ideal because doing so fail to integrate other summary-worthy features like sentence importance and positions. This paper presents MuchSUM, a better approach for extractive text summarization. MuchSUM is a multi-channel graph convolutional network designed to explicitly incorporate multiple salient summary-worthy features. Specifically, we introduce three specific graph channels to encode the node textual features, node centrality features, and node position features, respectively, under bipartite word-sentence heterogeneous graphs. Then, a cross-channel convolution operation is designed to distill the common graph representations shared by different channels. Finally, the sentence representations of each channel are fused for extractive summarization. We also investigate three weighted graphs in each channel to infuse edge features for graph-based summarization modeling. Experimental results demonstrate our model can achieve considerable performance compared with some BERT-initialized graph-based extractive summarization systems.

Summarizing user reviews and classifying user sentiment are two critical tasks for modern e-commerce platforms. These two tasks can benefit each other by capturing the shared linguistic features. However, such a relationship has not been fully exploited by existing research on domain-specific contextual representations. This work explores a win-win strategy for a multi-task framework with three stages: general pre-training, adaptive pre-training, and collaborative fine-tuning. The task-adaptive continual pre-training on a language model can obtain domain-specific contextual representations, further used to improve two related tasks, sentiment classification and review summarization during the collaborative fine-tuning. Meanwhile, to effectively capture sentiment-oriented domain-specific contextual representations, we introduce a novel task-adaptive pre-training procedure, which adds a sentiment prediction task during the adaptive pre-training. Extensive experiments conducted on two adaption scenarios of a general-to-single domain and a general-to-multiple domain show that our framework outperforms state-of-the-art methods.

Abstractive summarization generates a concise summary to capture the key ideas of the source text. This task underpins important applications like information retrieval, document comprehension, and event tracking. While much progress has been achieved, state-of-the-art summarization approaches often fail to generate high-quality summaries to reproduce factual details accurately. One of the key limitations of existing solutions is that they are primarily concerned about extracting facts from the source text but overlook other crucial factual information, such as the related time, locations, reasons, consequences, purposes, participants and involved parties. Furthermore, the current summarization frameworks are inadequate in modeling the complex semantic relations among facts and the corresponding factual information, leaving much room for improvement. This paper presentsFFSum, a novel summarization framework for exploiting multi-grained factual information to improve text summarization. To this end,FFSumconstructs an individual fine-grained factual graph with multiple relations among facts and the corresponding factual information. It employs a fact-driven graph attention network to integrate multi-granular factual representations at the encoding stage. It then uses a hybrid pointer network to retrieve factual pieces from the graph for the summary generation. We evaluate theFFSumby applying it to two real-world datasets. Experimental results show that theFFSumconsistently outperforms a state-of-the-art approach across evaluation datasets.

Script event prediction (SEP) aims to choose a correct subsequent event from a candidate list, given a chain of ordered context events. Event representation learning has been proposed and successfully applied to this task. Most previous methods learning representations mainly focus on coarse-grained connections at event or chain level, while ignoring more fine-grained connections between events. Here we propose a novel framework which can enhance the representation learning of events by mining their connections at multiple granularity levels, including argument level, event level and chain level. In our method, we first employ a masked self-attention mechanism to model the relations between the components of events (i.e. arguments). Then, a directed graph convolutional network is further utilized to model the temporal or causal relations between events in the chain. Finally, we introduce an attention module to the context event chain, so as to dynamically aggregate context events with respect to the current candidate event. By fusing threefold connections in a unified framework, our approach can learn more accurate argument/event/chain representations, and thus leads to better prediction performance. Comprehensive experiment results on public New York Times corpus demonstrate that our model outperforms other state-of-the-art baselines. Our code is available in https://github.com/YueAWu/MCer.

Aspect-based sentiment classification aims to identify sentiment polarity expressed towards a given opinion target in a sentence. The sentiment polarity of the target is not only highly determined by sentiment semantic context but also correlated with the concerned opinion target. Existing works cannot effectively capture and store the inter-dependence between the opinion target and its context. To solve this issue, we propose a novel model of Attentive Neural Turing Machines (ANTM). Via interactive read-write operations between an external memory storage and a recurrent controller, ANTM can learn the dependable correlation of the opinion target to context and concentrate on crucial sentiment information. Specifically, ANTM separates the information of storage and computation, which extends the capabilities of the controller to learn and store sequential features. The read and write operations enable ANTM to adaptively keep track of the interactive attention history between memory content and controller state. Moreover, we append target entity embeddings into both input and output of the controller in order to augment the integration of target information. We evaluate our model on SemEval2014 dataset which contains reviews of Laptop and Restaurant domains and Twitter review dataset. Experimental results verify that our model achieves state-of-the-art performance on aspect-based sentiment classification.