Bing Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bing Wang has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Ximing Li
College of Computer Science and Technology, Jilin University, Changchun, China
21 shared publications - Changchun Li
College of Computer Science and Technology, Jilin University, Changchun, China
8 shared publications - Renchu Guan
Jilin University
8 shared publications - Bo Fu
Liaoning Normal University
6 shared publications - Changchun Li
Jilin University
6 shared publications Jihong Ouyang
College of Computer Science and Technology and Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University, Changchun, China
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3665-3676
Two important things you must know! Revisiting Clickbait Detection from Perspectives of Humans' Cognition and Emotion
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3665-3676
Open AccessTwo important things you must know! Revisiting Clickbait Detection from Perspectives of Humans' Cognition and Emotion
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3654-3664
Unveiling Color-induced Emotions latent in Image-Text Expressions from Dual Perceptual Pathways
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3654-3664
Open AccessUnveiling Color-induced Emotions latent in Image-Text Expressions from Dual Perceptual Pathways
- Open Access
- 19 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-34
Weakly-Supervised Learning with Partial Multi-Labels by Leveraging Dual Label Correlation Perspectives
Multi-Label Learning (MLL) refers to inducing multi-label prediction models from the precisely labeled training dataset. However, in many real-world scenarios, e.g., crowdsourcing annotations, the training datasets are often only partially valid, where each training instance is associated with a candidate label set, covering ground-truth labels but also with irrelevant ones. Naturally, learning with such datasets, formally referred to as Partial MLL (PML), involves many noisy supervised signals, hence imposing a significant challenge to the prediction model induction. To meet this challenge, we purify the noisy supervised signals by formulating the latent label distribution, i.e., the probability of a candidate label being a ground-truth one, and then jointly learn it with the prediction model by minimizing their regularized Wasserstein distance, i.e., a robust distance for distributions as well as involving label correlations. Therefore, we propose a novel PML method, namely Wasserstein PML with dual Label Correlation Perspectives (W pml 3 cp ), solved by gradient descent with an augmented Lagrange multiplier technique. To further enhance the robustness of W pml 3 cp against exceptionally high ratios of irrelevant labels, we extend it with a Dual-branch Competitive Cleansing mechanism, leading to W pml 3 cp -D. Besides, we also analyze the generalization error bound and time complexity of W pml 3 cp and W pml 3 cp -D. The extensive experiments are constructed by comparing W pml 3 cp and W pml 3 cp -D with existing PML baselines across synthetic and real-world datasets, and empirical results demonstrate that W pml 3 cp and W pml 3 cp -D can outperform the PML baselines in various noisy levels.
- 19 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-34
Open AccessWeakly-Supervised Learning with Partial Multi-Labels by Leveraging Dual Label Correlation Perspectives
Multi-Label Learning (MLL) refers to inducing multi-label prediction models from the precisely labeled training dataset. However, in many real-world scenarios, e.g., crowdsourcing annotations, the training datasets are often only partially valid, where each training instance is associated with a candidate label set, covering ground-truth labels but also with irrelevant ones. Naturally, learning with such datasets, formally referred to as Partial MLL (PML), involves many noisy supervised signals, hence imposing a significant challenge to the prediction model induction. To meet this challenge, we purify the noisy supervised signals by formulating the latent label distribution, i.e., the probability of a candidate label being a ground-truth one, and then jointly learn it with the prediction model by minimizing their regularized Wasserstein distance, i.e., a robust distance for distributions as well as involving label correlations. Therefore, we propose a novel PML method, namely Wasserstein PML with dual Label Correlation Perspectives (W pml 3 cp ), solved by gradient descent with an augmented Lagrange multiplier technique. To further enhance the robustness of W pml 3 cp against exceptionally high ratios of irrelevant labels, we extend it with a Dual-branch Competitive Cleansing mechanism, leading to W pml 3 cp -D. Besides, we also analyze the generalization error bound and time complexity of W pml 3 cp and W pml 3 cp -D. The extensive experiments are constructed by comparing W pml 3 cp and W pml 3 cp -D with existing PML baselines across synthetic and real-world datasets, and empirical results demonstrate that W pml 3 cp and W pml 3 cp -D can outperform the PML baselines in various noisy levels.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4778-4787
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critical research topic. Traditional MD approaches based on small models typically perform binary classification, e.g., real and fake, through a black-box process. Recently, the rise of Large Language Models (LLMs) has enabled explainable MD, where models generate rationales that explain their decisions, thereby enhancing transparency. Existing explainable MD methods primarily focus on crafting sophisticated prompts to elicit rationales from off-the-shelf LLMs. In this work, we propose a pipeline to fine-tune a dedicated LLM specifically for explainable MD. Our pipeline begins by collecting large-scale fact-checked articles, and then uses multiple strong LLMs to produce veracity predictions and rationales. To ensure high-quality training data, we leverage a filtering strategy that selects only the correct instances for fine-tuning. While this pipeline is intuitive and prevalent, our experiments reveal that naive filtering based solely on label correctness is insufficient in practice and suffers from two critical limitations: (1) Coarse-grained labels cause insufficient rationales: Rationales filtered solely based on binary labels are insufficient to adequately support their decisions; (2) Over-verification behavior causes unnecessary rationales: Stronger LLMs tend to exhibit over-verification behavior, producing excessively verbose and unnecessary rationales. To address these issues, we introduce LonsRex, a novel data synthesis pipeline to Locate Necessary and Sufficient Rationales for Explainable MD. Specifically, we propose a metric that quantifies the contribution of each verification step to the final prediction, thereby evaluating its necessity and sufficiency. Experimental results demonstrate that LonsRex improves the accuracy of baseline LLMs by approximately 22.97% and is comparable to larger LLMs. We will publicly release our 316k raw data and the filtered version by LonsRex.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4778-4787
Open AccessAre Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critical research topic. Traditional MD approaches based on small models typically perform binary classification, e.g., real and fake, through a black-box process. Recently, the rise of Large Language Models (LLMs) has enabled explainable MD, where models generate rationales that explain their decisions, thereby enhancing transparency. Existing explainable MD methods primarily focus on crafting sophisticated prompts to elicit rationales from off-the-shelf LLMs. In this work, we propose a pipeline to fine-tune a dedicated LLM specifically for explainable MD. Our pipeline begins by collecting large-scale fact-checked articles, and then uses multiple strong LLMs to produce veracity predictions and rationales. To ensure high-quality training data, we leverage a filtering strategy that selects only the correct instances for fine-tuning. While this pipeline is intuitive and prevalent, our experiments reveal that naive filtering based solely on label correctness is insufficient in practice and suffers from two critical limitations: (1) Coarse-grained labels cause insufficient rationales: Rationales filtered solely based on binary labels are insufficient to adequately support their decisions; (2) Over-verification behavior causes unnecessary rationales: Stronger LLMs tend to exhibit over-verification behavior, producing excessively verbose and unnecessary rationales. To address these issues, we introduce LonsRex, a novel data synthesis pipeline to Locate Necessary and Sufficient Rationales for Explainable MD. Specifically, we propose a metric that quantifies the contribution of each verification step to the final prediction, thereby evaluating its necessity and sufficiency. Experimental results demonstrate that LonsRex improves the accuracy of baseline LLMs by approximately 22.97% and is comparable to larger LLMs. We will publicly release our 316k raw data and the filtered version by LonsRex.
- 13 June 2026
- Published by Springer Nature in GeoInformatica
- Vol. 30 (1) , 20
Geo-textual rumor detection in location-based social media by decomposing spatial subspaces
- 13 June 2026
- Published by Springer Nature in GeoInformatica
- Vol. 30 (1) , 20
Geo-textual rumor detection in location-based social media by decomposing spatial subspaces
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1589-1603
Detecting Misinformation by Uncovering Commonsense Conflicts With LLM Workflows
The advancement of Internet technology has spurred a rise in the dissemination of misinformation, which has had profoundly negative impacts across a wide array of fields. To address this issue, the field of Misinformation Detection (MD), which focuses on the automated identification of online misinformation, has gained significant traction among researchers. In our study, we introduce an innovative plug-and-play augmentation technique for MD, termed DEtecting Misinformation by Uncovering Commonsense Conflict (Demuc). Our approach is grounded in previous psychological research that suggests that fake content often contains commonsense. Accordingly, we develop commonsense expressions for articles to highlight potential conflicts between the inferred commonsense triplets and the established ones derived from reliable commonsense reasoning tools. According to the used tools, we induce two variants Demuc-klm using the knowledge language model COMET and Demuc-llm using the large language models. These generated expressions are then applied as augmentations to each article, enabling any MD method to be trained on these augmented datasets. Additionally, we have manually compiled a new dataset CoMis, which consists exclusively of fake articles characterized by commonsense conflicts. By integrating Demuc with various existing MD frameworks and evaluating them on four public benchmark datasets and CoMis, our empirical findings show that both Demuc-klm and Demuc-llm consistently and significantly outperform current MD baselines, while also generating precise commonsense expressions.
- 5 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1589-1603
Detecting Misinformation by Uncovering Commonsense Conflicts With LLM Workflows
The advancement of Internet technology has spurred a rise in the dissemination of misinformation, which has had profoundly negative impacts across a wide array of fields. To address this issue, the field of Misinformation Detection (MD), which focuses on the automated identification of online misinformation, has gained significant traction among researchers. In our study, we introduce an innovative plug-and-play augmentation technique for MD, termed DEtecting Misinformation by Uncovering Commonsense Conflict (Demuc). Our approach is grounded in previous psychological research that suggests that fake content often contains commonsense. Accordingly, we develop commonsense expressions for articles to highlight potential conflicts between the inferred commonsense triplets and the established ones derived from reliable commonsense reasoning tools. According to the used tools, we induce two variants Demuc-klm using the knowledge language model COMET and Demuc-llm using the large language models. These generated expressions are then applied as augmentations to each article, enabling any MD method to be trained on these augmented datasets. Additionally, we have manually compiled a new dataset CoMis, which consists exclusively of fake articles characterized by commonsense conflicts. By integrating Demuc with various existing MD frameworks and evaluating them on four public benchmark datasets and CoMis, our empirical findings show that both Demuc-klm and Demuc-llm consistently and significantly outperform current MD baselines, while also generating precise commonsense expressions.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2945-2955
Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2945-2955
Open AccessVariety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations
- Open Access
Enhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of the current post but the image often presents partial scenes only. Our preliminary empirical results indicate that the image modality exactly contributes less to MMD. Upon this idea, we propose a new MMD method named RETSIMD. Specifically, we suppose that each text can be divided into several segments, and each text segment describes a partial scene that can be presented by an image. Accordingly, we split the text into a sequence of segments, and feed these segments into a pre-trained text-to-image generator to augment a sequence of images. We further incorporate two auxiliary objectives concerning text-image and image-label mutual information, and further post-train the generator over an auxiliary text-to-image generation benchmark dataset. Additionally, we propose a graph structure by defining three heuristic relationships between images, and use a graph neural network to generate the fused features. Extensive empirical results validate the effectiveness of RETSIMD.
Open AccessEnhancing Multimodal Misinformation Detection by Replaying the Whole Story from Image Modality Perspective
Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of the current post but the image often presents partial scenes only. Our preliminary empirical results indicate that the image modality exactly contributes less to MMD. Upon this idea, we propose a new MMD method named RETSIMD. Specifically, we suppose that each text can be divided into several segments, and each text segment describes a partial scene that can be presented by an image. Accordingly, we split the text into a sequence of segments, and feed these segments into a pre-trained text-to-image generator to augment a sequence of images. We further incorporate two auxiliary objectives concerning text-image and image-label mutual information, and further post-train the generator over an auxiliary text-to-image generation benchmark dataset. Additionally, we propose a graph structure by defining three heuristic relationships between images, and use a graph neural network to generate the fused features. Extensive empirical results validate the effectiveness of RETSIMD.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5490-5498
Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5490-5498
Open AccessRemember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors