Recent self-supervised pre-training methods for object detection often rely on generic object proposals for localization and semantic feature learning for classification, but they yield limited improvements when applied to Detection Transformers (DETR) due to a lack of architectural alignment. Hence, we propose an elegant and versatile self-supervised framework tailored for DETR-like models called Distance-aware Multi-view Contrastive Learning (DisCo DETR). DisCo DETR enhances localization and semantic features through two core components. (i) Distance-aware Multi-view Object Query Fusion explicitly guides object queries to focus on spatially close objects across views, stabilizing training and improving localization accuracy. (ii) Contrastive Learning for DETR uses native bipartite matching to identify positive output pairs across views and pull them closer, enhancing semantic features discrimination with no extra matching. DisCo DETR can be seamlessly integrated into DETR-like models and achieves SOTA transfer performance on PASCAL VOC and COCO benchmarks across multiple variants.

Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

In Large Language Models (LLMs) generation, there exist knowledge conflicts and scenarios where parametric knowledge contradicts knowledge provided in the context.Previous works studied tuning, decoding algorithms, or locating and editing context-aware neurons to adapt LLMs to be faithful to new contextual knowledge.However, they are usually inefficient or ineffective for large models, not workable for black-box models, or unable to continuously adjust LLMs' sensitivity to the knowledge provided in the context.To mitigate these problems, we propose CSKS (Continuously Steering Knowledge Sensitivity), a simple framework that can steer LLMs' sensitivity to contextual knowledge continuously at a lightweight cost.Specifically, we tune two small LMs (i.e.proxy models) and use the difference in their output distributions to shift the original distribution of an LLM without modifying the LLM weights.In the evaluation process, we not only design synthetic data and fine-grained metrics to measure models' sensitivity to contextual knowledge but also use a real conflict dataset to validate CSKS's practical efficacy.Extensive experiments demonstrate that our framework achieves continuous and precise control over LLMs' sensitivity to contextual knowledge, enabling both increased sensitivity and reduced sensitivity, thereby allowing LLMs to prioritize either contextual or parametric knowledge as needed flexibly.Our data and code are available at https: //github.com/OliveJuiceLin/CSKS.

The rapid development of social media has led to a surge of eye-catching fake news on the Internet, with multimodal news comprising both images and text being particularly prevalent. To address the challenges of Multimodal Fake News Detection (MFND), numerous supervised task-specific Multimodal Small Language Models (MSLMs) have been developed. However, these models lack the breadth of knowledge and the depth of language understanding, which results in unsatisfactory adaptability, generalization, and explainability performance. To address these issues, we attempt to introduce Large Vision-Language Models (LVLMs), aiming to leverage the common sense understanding and logical reasoning abilities of LVLMs for the MFND task. We observed that LVLMs can generate reasonable analyses of news content from specific angles. However, when it comes to synthesizing these analyses for final judgment, their performance declines significantly, failing to meet the accuracy benchmarks set by existing MSLMs detection models. This reflects the need for a more effective way for LVLMs, which have not undergone task-specific training, to utilize their knowledge and capabilities. Based on these findings, we propose the Explainable Adaptive Rationale-Augmented Multimodal (EARAM) framework, which adaptively uses MSLMs to extract useful rationales from the multi-perspective analyses of LVLMs. After making judgments based on these rationales, EARAM then assists LVLMs in generating more reliable explanations. Extensive experiments demonstrate that our model not only achieves state-of-the-art results on widely used datasets but also significantly outperforms other models in terms of generalization and explainability.

Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy construction highly desirable. In this work, we introduce Chain-of-Layer which is an in-context learning framework designed to induct taxonomies from a given set of entities. Chain-of-Layer breaks down the task into selecting relevant candidate entities in each layer and gradually building the taxonomy from top to bottom. To minimize errors, we introduce the Ensemble-based Ranking Filter to reduce the hallucinated content generated at each iteration. Through extensive experiments, we demonstrate that Chain-of-Layer achieves state-of-the-art performance on four real-world benchmarks. Source code available at: https://github.com/qingkaizeng/chain-of-layer.

By design, large language models (LLMs) are static general-purpose models, expensive to retrain or update frequently. As they are increasingly adopted for knowledge-intensive tasks, it becomes evident that these design choices lead to failures to generate factual, relevant, and up-to-date knowledge. To this end, we propose Knowledge Card, a modular framework to plug in new factual and relevant knowledge into general-purpose LLMs. We first introduce knowledge cards---specialized language models trained on corpora from specific domains and sources. Knowledge cards serve as parametric repositories that are selected at inference time to generate background knowledge for the base LLM. We then propose three content selectors to dynamically select and retain information in documents generated by knowledge cards, specifically controlling for relevance, brevity, and factuality of outputs. Finally, we propose two complementary integration approaches to augment the base LLM with the (relevant, factual) knowledge curated from the specialized LMs. Through extensive experiments, we demonstrate that Knowledge Card achieves state-of-the-art performance on six benchmark datasets. Ultimately, Knowledge Card framework enables dynamic synthesis and updates of knowledge from diverse domains. Its modularity will ensure that relevant knowledge can be continuously updated through the collective efforts of the research community.

Large language models (LLMs) demonstrate remarkable performance on knowledge-intensive tasks, suggesting that real-world knowledge is encoded in their model parameters. However, besides explorations on a few probing tasks in limited knowledge domains, it is not well understood how to evaluate LLMs' knowledge systematically and how well their knowledge abilities generalize, across a spectrum of knowledge domains and progressively complex task formats. To this end, we propose KGQuiz, a knowledge-intensive benchmark to comprehensively investigate the knowledge generalization abilities of LLMs. KGQuiz is a scalable framework constructed from triplet-based knowledge, which covers three knowledge domains and consists of five tasks with increasing complexity: true-or-false, multiple-choice QA, blank filling, factual editing, and open-ended knowledge generation. To gain a better understanding of LLMs' knowledge abilities and their generalization, we evaluate 10 open-source and black-box LLMs on the KGQuiz benchmark across the five knowledge-intensive tasks and knowledge domains. Extensive experiments demonstrate that LLMs achieve impressive performance in straightforward knowledge QA tasks, while settings and contexts requiring more complex reasoning or employing domain-specific facts still present significant challenges. We envision KGQuiz as a testbed to analyze such nuanced variations in performance across domains and task formats, and ultimately to understand, evaluate, and improve LLMs' knowledge abilities across a wide spectrum of knowledge domains and tasks.

Evaluating the factual consistency of automatically generated summaries is essential for the progress and adoption of reliable summarization systems.Despite recent advances, existing factuality evaluation models are not robust, being especially prone to entity and relation errors in new domains.We propose FAC-TKB-a simple new approach to factuality evaluation that is generalizable across domains, in particular with respect to entities and relations.FACTKB is based on language models pretrained using facts extracted from external knowledge bases.We introduce three types of complementary factuality pretraining objectives based on entity-specific facts, facts extracted from auxiliary knowledge about entities, and facts constructed compositionally through knowledge base walks.The resulting factuality evaluation model achieves state-of-the-art performance on two in-domain news summarization benchmarks as well as on three outof-domain scientific literature datasets.Further analysis of FACTKB shows improved ability to detect erroneous entities and relations in summaries and is robust and easily generalizable across domains.Code and data are available at https://github.com/BunsenFeng/FactKB.

Online movie review platforms are providing crowdsourced feedback for the film industry and the general public, while spoiler reviews greatly compromise user experience.Although preliminary research efforts were made to automatically identify spoilers, they merely focus on the review content itself, while robust spoiler detection requires putting the review into the context of facts and knowledge regarding movies, user behavior on film review platforms, and more.In light of these challenges, we first curate a large-scale networkbased spoiler detection dataset LCS and a comprehensive and up-to-date movie knowledge base UKM.We then propose MVSD, a novel Multi-View Spoiler Detection framework that takes into account the external knowledge about movies and user activities on movie review platforms.Specifically, MVSD constructs three interconnecting heterogeneous information networks to model diverse data sources and their multi-view attributes, while we design and employ a novel heterogeneous graph neural network architecture for spoiler detection as node-level classification.Extensive experiments demonstrate that MVSD advances the state-of-the-art on two spoiler detection datasets, while the introduction of external knowledge and user interactions help ground robust spoiler detection.Our data and code are available at https://github.com/Arthur-

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 \url{https://twibot22.github.io/}.