Detecting harmful memes is crucial for safeguarding the integrity and harmony of online environments, yet existing detection methods are often resource-intensive, inflexible, and lacking explainability, limiting their applicability in assisting real-world web content moderation. We propose U-CoT+, a resource-efficient framework that prioritizes accessibility, flexibility and transparency in harmful meme detection by fully harnessing the capabilities of lightweight unimodal large language models (LLMs). Instead of directly prompting or fine-tuning large multimodal models (LMMs) as black-box classifiers, we avoid immediate reasoning over complex visual inputs but decouple meme content recognition from meme harmfulness analysis through a high-fidelity meme-to-text pipeline, which collaborates lightweight LMMs and LLMs to convert multimodal memes into natural language descriptions that preserve critical visual information, thus enabling text-only LLMs to "see" memes by "reading". Grounded in textual inputs, we further guide unimodal LLMs' reasoning under zero-shot Chain-of-Thoughts (CoT) prompting with targeted, interpretable, context-aware, and easily obtained human-crafted guidelines, thus providing accountable step-by-step rationales, while enabling flexible and efficient adaptation to diverse sociocultural criteria of harmfulness. Extensive experiments on seven benchmark datasets show that U-CoT+ achieves performance comparable to resource-intensive baselines, highlighting its effectiveness and potential as a scalable, explainable, and low-resource solution to support harmful meme detection.

Hierarchical topic modeling aims to discover latent topics from a corpus and organize them into a hierarchy to understand documents with desirable semantic granularity. However, existing work struggles with producing topic hierarchies of low affinity, rationality, and diversity, which hampers document understanding. To overcome these challenges, we in this paper propose Transport Plan and Context-aware Hierarchical Topic Model (TraCo). Instead of early simple topic dependencies, we propose a transport plan dependency method. It constrains dependencies to ensure their sparsity and balance, and also regularizes topic hierarchy building with them. This improves affinity and diversity of hierarchies. We further propose a context-aware disentangled decoder. Rather than previously entangled decoding, it distributes different semantic granularity to topics at different levels by disentangled decoding. This facilitates the rationality of hierarchies. Experiments on benchmark datasets demonstrate that our method surpasses state-of-the-art baselines, effectively improving the affinity, rationality, and diversity of hierarchical topic modeling with better performance on downstream tasks.

Fallacies are defective arguments with faulty reasoning.Detecting and classifying them is a crucial NLP task to prevent misinformation, manipulative claims, and biased decisions.However, existing fallacy classifiers are limited by the requirement for sufficient labeled data for training, which hinders their out-of-distribution (OOD) generalization abilities.In this paper, we focus on leveraging Large Language Models (LLMs) for zero-shot fallacy classification.To elicit fallacy-related knowledge and reasoning abilities of LLMs, we propose diverse single-round and multi-round prompting schemes, applying different taskspecific instructions such as extraction, summarization, and Chain-of-Thought reasoning.With comprehensive experiments on benchmark datasets, we suggest that LLMs could be potential zero-shot fallacy classifiers.In general, LLMs under single-round prompting schemes have achieved acceptable zeroshot performances compared to the best fullshot baselines and can outperform them in all OOD inference scenarios and some opendomain tasks.Our novel multi-round prompting schemes can effectively bring about more improvements, especially for small LLMs.Our analysis further underlines the future research on zero-shot fallacy classification.Codes and data are available at: https://github.com/ panFJCharlotte98/Fallacy_Detection.

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to malicious attacks. In this work, we raise security concerns regarding this paradigm. Our studies demonstrate that an attacker can manipulate the behavior of large language models by poisoning the demonstration context, without the need for fine-tuning the model. Specifically, we design a new backdoor attack method, named ICLAttack, to target large language models based on in-context learning. Our method encompasses two types of attacks: poisoning demonstration examples and poisoning demonstration prompts, which can make models behave in alignment with predefined intentions. ICLAttack does not require additional fine-tuning to implant a backdoor, thus preserving the model’s generality. Furthermore, the poisoned examples are correctly labeled, enhancing the natural stealth of our attack method. Extensive experimental results across several language models, ranging in size from 1.3B to 180B parameters, demonstrate the effectiveness of our attack method, exemplified by a high average attack success rate of 95.0% across the three datasets on OPT models.

The height and stagger of the contact wire directly affect the energy supply of high-speed trains. To ensure the operation safety, there is an urgent demand for high-speed railways to measure the static parameters of contact wires all over the line with high precision and efficiency. However, this issue is barely discussed. Concerning the issue, this paper proposes a UAV-LiDAR-based measuring framework for the static height and stagger of high-speed railway contact wire. By mounting LiDAR on the UAV, the framework can efficiently collect data from the lines in service without occupying the train operating-diagrams. It is extremely significant for the high-speed and high-density railways. Then, we present self-adaptive extraction algorithms to extract critical infrastructures (rails, contact wires, masts and other suspensions) based on their specific geometric characteristics as well as the continuity and consistency of the spatial distributions along the line. Finally, the height and stagger are calculated by formulas automatically. To verify the framework in practice, we tested it on Beijing-Shanghai high-speed railway, which is the busiest high-speed railway in China. It is shown that the measurement error is within 9mm and the framework has potential to reform the inspection of high-speed railways.