Highly realistic human-machine interaction is challenging for open-domain dialogue systems. Although existing methods have achieved notable progress by leveraging various interaction factors (e.g., emotion, personality, topic) for delivering human-like (e.g., empathetic, personalized and semantically-consistent) responses, they typically model such factor alone and thus easily suffer from low-quality response generation issue. We attribute this limitation to the neglect of implicit-correlations among factors. Furthermore, different factors may alternately dominate token-level response generation during decoding, making it harder to generate high-quality responses by applying various factors at the sentence level. To address the issue, we present a unified response generation framework, which is capable of simultaneously modeling Complex Multiple Interaction Factors (named CoMIF) to generate human-like conversations. To model the implicit correlations among factors, CoMIF first employ a dynamic perception module to construct a directed collaborative-graph to jointly learn the dynamics over time of each factor, as well as the cross-dependencies among them. Additionally, we also design a scalable post-adaptation module to introduce token-level factor signals to generate more human-like responses with appropriately multiple factors. Extensive experiments over multiple datasets demonstrate that the proposed method achieves the superior performance in generating more human-like responses with appropriate multiple-factors, as compared to the state-of-the-art methods.

Moment Retrieval aims to locate specific video segments related to the given text. Recently, DETR-based methods, originating from Object Detection, have emerged as effective solutions for Moment Retrieval. These approaches focus on multimodal feature fusion and refining Queries composed of span anchor and content embedding. Despite the success, they often overlook the video-text instance related information in Query Initialization and the crucial guidance role of span anchors in Query Refinement, leading to inaccurate predictions. To address this, we propose a novel Span Aware DEtection TRansformer (SA-DETR) that leverages the importance of instance related span anchors. To fully leverage the instance related information, we generate span anchors based on video-text pair rather than using learnable parameters, as is common in conventional DETR-based methods, and supervise them with GT labels. To effectively exploit the correspondence between span anchors and video clips, we enhance content embedding guided by textual features and generate Gaussian mask to modulate the interaction between content embedding and fusion features. Furthermore, we explore the feature alignment across various stages and granularities and apply denoise learning to boost the span awareness of the model. Extensive experiments on QVHighlights, Charades-STA, and TACoS demonstrate the effectiveness of our approach.

Recently, prompt-tuning with pre-trained language models (PLMs) has demonstrated the significantly enhancing ability of relation extraction (RE) tasks. However, in low-resource scenarios, where the available training data is scarce, previous prompt-based methods may still perform poorly for prompt-based representation learning due to a superficial understanding of the relation. To this end, we highlight the importance of learning high-quality relation representation in low-resource scenarios for RE, and propose a novel prompt-based relation representation method, named MVRE (Multi-View Relation Extraction), to better leverage the capacity of PLMs to improve the performance of RE within the low-resource prompt-tuning paradigm. Specifically, MVRE decouples each relation into different perspectives to encompass multi-view relation representations for maximizing the likelihood during relation inference. Furthermore, we also design a Global-Local loss and a Dynamic-Initialization method for better alignment of the multi-view relation-representing virtual words, containing the semantics of relation labels during the optimization learning process and initialization. Extensive experiments on three benchmark datasets show that our method can achieve state-of-the-art in low-resource settings.

Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning. NMNs decompose the complex question into several sub-tasks using instance-modules from the reasoning paths of that question and then exploit intermediate supervisions to guide answer prediction, thereby improving inference interpretability. However, their performance may be hindered due to sketchy modeling of intermediate supervisions. For instance, (1) a prior assumption that each instance-module refers to only one grounded object yet overlooks other potentially associated grounded objects, impeding full cross-modal alignment learning; (2) IoU-based intermediate supervisions may introduce noise signals as the bounding box overlap issue might guide the model's focus towards irrelevant objects. To address these issues, a novel method, Detection-based Intermediate Supervision (DIS), is proposed, which adopts a generative detection framework to facilitate multiple grounding supervisions via sequence generation. As such, DIS offers more comprehensive and accurate intermediate supervisions, thereby boosting answer prediction performance. Furthermore, by considering intermediate results, DIS enhances the consistency in answering compositional questions and their sub-questions. Extensive experiments demonstrate the superiority of our proposed DIS, showcasing both improved accuracy and state-of-the-art reasoning consistency compared to prior approaches.

Recently, Temporal Knowledge Graph Forecasting (TKGF) has emerged as a pivotal domain for forecasting future events.Unlike black-box neural network methods, rule-based approaches are lauded for their efficiency and interpretability.For this line of work, it is crucial to correctly estimate the predictive effectiveness of the rules, i.e., the confidence.However, the existing literature lacks in-depth investigation into how confidence evolves with time.Moreover, inaccurate and heuristic confidence estimation limits the performance of rule-based methods.To alleviate such issues, we propose a framework named TempValid to explicitly model the temporal validity of rules for TKGF.Specifically, we design a time function to model the interaction between temporal information with confidence.TempValid conceptualizes confidence and other coefficients as learnable parameters to avoid inaccurate estimation and combinatorial explosion.Furthermore, we introduce a rule-adversarial negative sampling and a time-aware negative sampling strategies to facilitate TempValid learning.Extensive experiments show that TempValid significantly outperforms previous state-of-theart (SOTA) rule-based methods on six TKGF datasets.Moreover, it exhibits substantial advancements in cross-domain and resourceconstrained rule learning scenarios.

Temporal Knowledge Graph (TKG) is an extension of regular knowledge graph by attaching the time scope. Existing temporal knowledge graph question answering (TKGQA) models solely approach simple questions, owing to the prior assumption that each question only contains a single temporal fact with explicit/implicit temporal constraints. Hence, they perform poorly on questions which own multiple temporal facts. In this paper, we propose Joint Multi Facts Reasoning Network (JMFRN), to jointly reasoning multiple temporal facts for accurately answering complex temporal questions. Specifically, JMFRN first retrieves question-related temporal facts from TKG for each entity of the given complex question. For joint reasoning, we design two different attention (i.e., entity-aware and time-aware) modules, which are suitable for universal settings, to aggregate entities and timestamps information of retrieved facts. Moreover, to filter incorrect type answers, we introduce an additional answer type discrimination task. Extensive experiments demonstrate our proposed method significantly outperforms the state-of-art on the wellknown complex temporal question benchmark TimeQuestions.

Scene Graph Generation(SGG) is a scene understanding task that aims at identifying object entities and reasoning their relationships within a given image. In contrast to prevailing two-stage methods based on a large object detector (e.g., Faster R-CNN), one-stage methods integrate a fixed-size set of learnable queries to jointly reason relational triplets . This paradigm demonstrates robust performance with significantly reduced parameters and computational overhead. However, the challenge in one-stage methods stems from the issue of weak entanglement, wherein entities involved in relationships require both coupled features shared within triplets and decoupled visual features. Previous methods either adopt a single decoder for coupled triplet feature modeling or multiple decoders for separate visual feature extraction but fail to consider both. In this paper, we introduce UniQ, a Unified decoder with task-specific Queries architecture, where task-specific queries generate decoupled visual features for subjects, objects, and predicates respectively, and unified decoder enables coupled feature modeling within relational triplets. Experimental results on the Visual Genome dataset demonstrate that UniQ has superior performance to both one-stage and two-stage methods.

Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly challenging. Despite numerous proposals for effective methods, a substantial memory overhead remains for gradient computations during updates. \thm{Can we fine-tune a series of task-specific small models and transfer their knowledge directly to a much larger model without additional training?} In this paper, we explore weak-to-strong specialization using logit arithmetic, facilitating a direct answer to this question. Existing weak-to-strong methods often employ a static knowledge transfer ratio and a single small model for transferring complex knowledge, which leads to suboptimal performance. To surmount these limitations, we propose a dynamic logit fusion approach that works with a series of task-specific small models, each specialized in a different task. This method adaptively allocates weights among these models at each decoding step, learning the weights through Kullback-Leibler divergence constrained optimization problems. We conduct extensive experiments across various benchmarks in both single-task and multi-task settings, achieving leading results. By transferring expertise from the 7B model to the 13B model, our method closes the performance gap by 96.4\% in single-task scenarios and by 86.3\% in multi-task scenarios compared to full fine-tuning of the 13B model. Notably, we achieve surpassing performance on unseen tasks. Moreover, we further demonstrate that our method can effortlessly integrate in-context learning for single tasks and task arithmetic for multi-task scenarios.

In the era of large language models, model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. However, two challenges remain: (a) interference between different models and (b) heterogeneous data during testing. Traditional model merging methods often show significant performance gaps compared to fine-tuned models due to these issues. Additionally, a one-size-fits-all model lacks flexibility for diverse test data, leading to performance degradation. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. In view of this, we propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input. This approach narrows the performance gap between merged and fine-tuned models and improves adaptability to heterogeneous data. Extensive experiments on $20$ datasets for both language and vision tasks demonstrate the effectiveness of our method, showing an average improvement of $28.34\%$ in absolute normalized score for discriminative tasks and even surpassing the fine-tuned upper bound on the generative tasks.

Session-based recommendation (SBR) is a challenging task, which aims to predict users’ future interests based on anonymous behavior sequences. Existing methods leverage powerful representation learning approaches to encode sessions into a low-dimensional space. However, despite such achievements, the existing studies focus on the instance-level session learning, while neglecting the group-level users’ preferences (e.g., the common preferences of group users in repeat consumption). To this end, we propose a novelRepeat-awareNeuralMechanism forSession-basedRecommendation (RNMSR). In RNMSR, we propose to learn the user preference from two levels: (i)instance-level, which employs GNNs on a similarity-based item-pairwise session graph to capture the users’ preference in instance-level. (ii)group-level, which converts sessions into group-level behavior patterns to model the group-level users’ preferences. In RNMSR, we combine instance-level and group-level user preference to model the repeat consumption of users, i.e., whether users take repeated consumption and which items are preferred by users. Extensive experiments are conducted on three real-world datasets, i.e., Diginetica, Yoochoose, and Nowplaying, demonstrating that the proposed method consistently achieves state-of-the-art performance in all the tests.

Bundle recommendation aims to recommend a bundle of items for the user to purchase together, for which two scenarios (i.e.Next-bundle recommendation and Within-bundle recommendation) are explored to recommend a specific bundle of items for the user and a specific item to fill the user's current bundle, respectively. Previous works largely model the user's preference with a uniform intent, without considering the diversity of intents when adopting the items within the bundle. In the real scenario of bundle recommendation, user intents modeling actually needs to be considered from three hierarchical levels, for that: a user's intents may be naturally distributed in different bundles (user level), one bundle may contain multiple intents of a user (bundle level), and an item in different bundles may also present different user intents (item level). To this end, we develop a novel model,HierarchicalIntentDisentangleGraphNetworks (HIDGN) for bundle recommendation. HIDGN is capable of capturing the diversity of the user's intent precisely and comprehensively from the hierarchical structure with an cross-task intent contrastive learning, which is unified with the supervised next-/within-bundle recommendation sub-tasks as a multi-task framework. Extensive experiments on three benchmark datasets demonstrate that HIDGN outperforms the state-of-the-art methods by 43.0%, 13.2%, and 73.3%, respectively.

Aspect Sentiment Triplet Extraction (ASTE) has become an emerging task in sentiment analysis research, aiming to extract triplets of the aspect term, its corresponding opinion term, and its associated sentiment polarity from a given sentence. Recently, many neural networks based models with different tagging schemes have been proposed, but almost all of them have their limitations: heavily relying on 1) prior assumption that each word is only associated with a single role (e.g., aspect term, or opinion term, etc. ) and 2) word-level interactions and treating each opinion/aspect as a set of independent words. Hence, they perform poorly on the complex ASTE task, such as a word associated with multiple roles or an aspect/opinion term with multiple words. Hence, we propose a novel approach, Span TAgging and Greedy infErence (STAGE), to extract sentiment triplets in span-level, where each span may consist of multiple words and play different roles simultaneously. To this end, this paper formulates the ASTE task as a multi-class span classification problem. Specifically, STAGE generates more accurate aspect sentiment triplet extractions via exploring span-level information and constraints, which consists of two components, namely, span tagging scheme and greedy inference strategy. The former tag all possible candidate spans based on a newly-defined tagging set. The latter retrieves the aspect/opinion term with the maximum length from the candidate sentiment snippet to output sentiment triplets. Furthermore, we propose a simple but effective model based on the STAGE, which outperforms the state-of-the-arts by a large margin on four widely-used datasets. Moreover, our STAGE can be easily generalized to other pair/triplet extraction tasks, which also demonstrates the superiority of the proposed scheme STAGE.

Conversational recommender systems (CRS) aim to timely trace the dynamic interests of users through dialogues and generate relevant responses for item recommendations.Recently, various external knowledge bases (especially knowledge graphs) are incorporated into CRS to enhance the understanding of conversation contexts.However, recent reasoning-based models heavily rely on simplified structures such as linear structures or fixed-hierarchical structures for causality reasoning, hence they cannot fully figure out sophisticated relationships among utterances with external knowledge.To address this, we propose a novel Treestructure Reasoning schEmA named TREA.TREA constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities, and fully utilizes historical conversations to generate more reasonable and suitable responses for recommended results.Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach.Our

Generalization beyond in-domain experience to out-of-distribution data is of paramount significance in the AI domain. Of late, state-of-the-art Visual Question Answering (VQA) models have shown impressive performance on in-domain data, partially due to the language prior bias which, however, hinders the generalization ability in practice. This paper attempts to provide new insights into the influence of language modality on VQA performance from an empirical study perspective. To achieve this, we conducted a series of experiments on six models. The results of these experiments revealed that, 1) apart from prior bias caused by question types, there is a notable influence of postfix-related bias in inducing biases, and 2) training VQA models with word-sequence-related variant questions demonstrated improved performance on the out-of-distribution benchmark, and the LXMERT even achieved a 10-point gain without adopting any debiasing methods. We delved into the underlying reasons behind these experimental results and put forward some simple proposals to reduce the models' dependency on language priors. The experimental results demonstrated the effectiveness of our proposed method in improving performance on the out-of-distribution benchmark, VQA-CPv2. We hope this study can inspire novel insights for future research on designing bias-reduction approaches.

Conversational recommendation systems (CRS) aim to interactively acquire user preferences and accordingly recommend items to users. Accurately learning the dynamic user preferences is of crucial importance for CRS. Previous works learn the user preferences with pairwise relations from the interactive conversation and item knowledge, while largely ignoring the fact that factors for a relationship in CRS are multiplex. Specifically, the user likes/dislikes the items that satisfy some attributes (Like/Dislike view). Moreover social influence is another important factor that affects user preference towards the item (Social view), while is largely ignored by previous works in CRS. The user preferences from these three views are inherently different but also correlated as a whole. The user preferences from the same views should be more similar than that from different views. The user preferences from Like View should be similar to Social View while different from Dislike View. To this end, we propose a novel model, namely Multi-view Hypergraph Contrastive Policy Learning (MHCPL). Specifically, MHCPL timely chooses useful social information according to the interactive history and builds a dynamic hypergraph with three types of multiplex relations from different views. The multiplex relations in each view are successively connected according to their generation order in the interactive conversation. A hierarchical hypergraph neural network is proposed to learn user preferences by integrating information of the graphical and sequential structure from the dynamic hypergraph. A cross-view contrastive learning module is proposed to maintain the inherent characteristics and the correlations of user preferences from different views. Extensive experiments conducted on benchmark datasets demonstrate that MHCPL outperforms the state-of-the-art methods.

Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.

Sequential recommendation (SR) aims to predict the subsequent behaviors of users by understanding their successive historical behaviors. Recently, some methods for SR are devoted to alleviating the data sparsity problem (i.e., limited supervised signals for training), which take account of contrastive learning to incorporate self-supervised signals into SR. Despite their achievements, it is far from enough to learn informative user/item embeddings due to the inadequacy modeling of complex collaborative information and co-action information, such as user-item relation, user-user relation, and item-item relation. In this paper, we study the problem of SR and propose a novel multi-level contrastive learning framework for sequential recommendation, named MCLSR. Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i.e., interest- and feature-level). Specifically, the interest-level contrastive mechanism jointly learns the collaborative information with the sequential transition patterns, and the feature-level contrastive mechanism re-observes the relation between users and items via capturing the co-action information (i.e., co-occurrence). Extensive experiments on four real-world datasets show that the proposed MCLSR outperforms the state-of-the-art methods consistently.

Incorporating Knowledge Graphs (KG) into recommeder system as side information has attracted considerable attention. Recently, the technical trend of Knowledge-aware Recommendation (KGR) is to develop end-to-end models based on graph neural networks (GNNs). However, the extremely sparse user-item interactions significantly degrade the performance of the GNN-based models, from the following aspects: 1) the sparse interaction, itself, means inadequate supervision signals and limits the supervised GNN-based models; 2) the combination of sparse interactions (CF part) and redundant KG facts (KG part) further results in an unbalanced information utilization. Besides, the GNN paradigm aggregates local neighbors for node representation learning, while ignoring the non-local KG facts and making the knowledge extraction insufficient. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring contrastive learning in KGR and propose a novel multi-level interactive contrastive learning mechanism, to alleviate the aforementioned challenges. Different from traditional contrastive learning methods which contrast nodes of two generated graph views, interactive contrastive mechanism conducts layer-wise self-supervised learning by contrasting layers of different parts within graphs, which is also an "interaction" action. Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR. Then an intra-graph level interactive contrastive learning is performed within each local/non-local graph, which contrasts layers of the CF and KG parts, for more consistent information leveraging. Besides, an inter-graph level interactive contrastive learning is performed between the local and non-local graphs, for sufficiently and coherently extracting non-local KG signals. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/KGIC.