Shifting Long-Context LLMs Research from Input to Output

Recent advancements in long-context Large Language Models (LLMs) have primarily concentrated on processing extended input contexts, resulting in significant strides in long-context comprehension. However, the equally critical aspect of generating long-form outputs has received comparatively less attention. This paper advocates for a paradigm shift in NLP research toward addressing the challenges of long-output generation. Tasks such as novel writing, long-term planning, and complex reasoning require models to understand extensive contexts and produce coherent, contextually rich, and logically consistent extended text. These demands highlight a critical gap in current LLM capabilities. We underscore the importance of this under-explored domain and call for focused efforts to develop foundational LLMs tailored for generating high-quality, long-form outputs, which hold immense potential for real-world applications.

Unveiling the Capabilities of Large Language Models in Detecting Offensive Language with Annotation Disagreement

LLMs are widely used for offensive language detection due to their advanced capability. However, the challenges posed by human annotation disagreement in real-world datasets remain underexplored. These disagreement samples are difficult to detect due to their ambiguous nature. Additionally, the confidence of LLMs in processing disagreement samples can provide valuable insights into their alignment with human annotators. To address this gap, we systematically evaluate the ability of LLMs to detect offensive language with annotation disagreement. We compare the binary accuracy of multiple LLMs across varying annotation agreement levels and analyze the relationship between LLM confidence and annotation agreement. Furthermore, we investigate the impact of disagreement samples on LLM decision-making during few-shot learning and instruction fine-tuning. Our findings highlight the challenges posed by disagreement samples and offer guidance for improving LLM-based offensive language detection.

Contrastive Token-level Explanations for Graph-based Rumour Detection

The widespread use of social media has accelerated the dissemination of information, but it has also facilitated the spread of harmful rumours, which can disrupt economies, influence political outcomes, and exacerbate public health crises, such as the COVID-19 pandemic. While Graph Neural Network (GNN)-based approaches have shown significant promise in automated rumour detection, they often lack transparency, making their predictions difficult to interpret. Existing graph explainability techniques fall short in addressing the unique challenges posed by the dependencies among feature dimensions in high-dimensional text embeddings used in GNN-based models. In this paper, we introduce Contrastive Token Layerwise Relevance Propagation (CT-LRP), a novel framework designed to enhance the explainability of GNN-based rumour detection. CT-LRP extends current graph explainability methods by providing token-level explanations that offer greater granularity and interpretability. We evaluate the effectiveness of CT-LRP across multiple GNN models trained on three publicly available rumour detection datasets, demonstrating that it consistently produces high-fidelity, meaningful explanations, paving the way for more robust and trustworthy rumour detection systems.

Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection

Detecting hate speech in online content is essential to ensuring safer digital spaces. While significant progress has been made in text and meme modalities, video-based hate speech detection remains under-explored, hindered by a lack of annotated datasets and the high cost of video annotation. This gap is particularly problematic given the growing reliance on large models, which demand substantial amounts of training data. To address this challenge, we leverage meme datasets as both a substitution and an augmentation strategy for training hateful video detection models. Our approach introduces a human-assisted reannotation pipeline to align meme dataset labels with video datasets, ensuring consistency with minimal labeling effort. Using two state-of-the-art vision-language models, we demonstrate that meme data can substitute for video data in resource-scarce scenarios and augment video datasets to achieve further performance gains. Our results consistently outperform state-of-the-art benchmarks, showcasing the potential of cross-modal transfer learning for advancing hateful video detection. Dataset and code are available at https://github.com/Social-AI-Studio/CrossModalTransferLearning.

Fairness And Performance In Harmony: Data Debiasing Is All You Need

Fairness in both machine learning (ML) predictions and human decisions is critical, with ML models prone to algorithmic and data bias, and human decisions affected by subjectivity and cognitive bias. This study investigates fairness using a real-world university admission dataset with 870 profiles, leveraging three ML models, namely XGB, Bi-LSTM, and KNN. Textual features are encoded with BERT embeddings. For individual fairness, we assess decision consistency among experts with varied backgrounds and ML models, using a consistency score. Results show ML models outperform humans in fairness by 14.08% to 18.79%. For group fairness, we propose a gender-debiasing pipeline and demonstrate its efficacy in removing gender-specific language without compromising prediction performance. Post-debiasing, all models maintain or improve their classification accuracy, validating the hypothesis that fairness and performance can coexist. Our findings highlight ML's potential to enhance fairness in admissions while maintaining high accuracy, advocating a hybrid approach combining human judgement and ML models.

Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks

How objective and unbiased are we while making decisions? This work investigates cognitive bias identification in high-stake decision making process by human experts, questioning its effectiveness in real-world settings, such as candidates assessments for university admission. We begin with a statistical analysis assessing correlations among different decision points among in the current process, which discovers discrepancies that imply cognitive bias and inconsistency in decisions. This motivates our exploration of bias-aware AI-augmented workflow that surpass human judgment. We propose BGM-HAN, an enhanced Hierarchical Attention Network with Byte-Pair Encoding, Gated Residual Connections and Multi-Head Attention. Using it as a backbone model, we further propose a Shortlist-Analyse-Recommend (SAR) agentic workflow, which simulate real-world decision-making. In our experiments, both the proposed model and the agentic workflow significantly improves on both human judgment and alternative models, validated with real-world data.

Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning

The widespread presence of hate speech on the internet, including formats such as text-based tweets and vision-language memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored to specific modalities; however, there is a notable gap in transferring detection capabilities across different formats. This study conducts extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. Our findings demonstrate that text-based hate speech examples can significantly enhance the classification accuracy of vision-language hate speech. Moreover, text-based demonstrations outperform vision-language demonstrations in few-shot learning settings. These results highlight the effectiveness of cross-modality knowledge transfer and offer valuable insights for improving hate speech detection systems.

LongGenbench: Benchmarking Long-Form Generation in Long Context LLMs

The abilities of long-context language models (LMs) are often evaluated using the "Needle-in-a-Haystack" (NIAH) test, which comprises tasks designed to assess a model's ability to identify specific information ("needle") within large text sequences ("haystack"). While these benchmarks measure how well models understand long-context input sequences, they do not effectively gauge the quality of long-form text generation--a critical aspect for applications such as design proposals and creative writing. To address this gap, we have introduced a new long-form text evaluation benchmark, LongGenbench, which tests models' ability to identify specific events within generated long text sequences. In this benchmark, we prompt long-context LMs to create long-form text that must include particular events or constraints and evaluate their ability to incorporate these elements. We evaluated ten long-context LMs across four distinct scenarios, three types of prompt instructions, and two different generation-length settings (16K and 32K). Although these models perform well on NIAH benchmarks, none demonstrated satisfactory performance on the LongGenbench, raising concerns about their ability to generate coherent long-form text that follows instructions. Additionally, as the length of the generated text increases, all models exhibit a significant drop in performance.

Spinning the Golden Thread: Benchmarking Long-Form Generation in Language Models

The abilities of long-context language models (LMs) are often evaluated using the "Needle-in-a-Haystack" (NIAH) test, which comprises tasks designed to assess a model's ability to identify specific information ("needle") within large text sequences ("haystack"). While these benchmarks measure how well models understand long-context input sequences, they do not effectively gauge the quality of long-form text generation--a critical aspect for applications such as design proposals and creative writing. To address this gap, we have introduced a new long-form text evaluation benchmark, Spinning the Golden Thread (SGT), which tests models' ability to identify specific events within generated long text sequences. In this benchmark, we prompt long-context LMs to create long-form text that must include particular events or constraints and evaluate their ability to incorporate these elements. We evaluated ten long-context LMs across four distinct scenarios, three types of prompt instructions, and two different generation-length settings (16K and 32K). Although these models perform well on NIAH benchmarks, none demonstrated satisfactory performance on the Spinning the Golden Thread, raising concerns about their ability to generate coherent long-form text that follows instructions. Additionally, as the length of the generated text increases, all models exhibit a significant drop in performance.

MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili

Hate speech is a pressing issue in modern society, with significant effects both online and offline. Recent research in hate speech detection has primarily centered on text-based media, largely overlooking multimodal content such as videos. Existing studies on hateful video datasets have predominantly focused on English content within a Western context and have been limited to binary labels (hateful or non-hateful), lacking detailed contextual information. This study presents MultiHateClip1 , an novel multilingual dataset created through hate lexicons and human annotation. It aims to enhance the detection of hateful videos on platforms such as YouTube and Bilibili, including content in both English and Chinese languages. Comprising 2,000 videos annotated for hatefulness, offensiveness, and normalcy, this dataset provides a cross-cultural perspective on gender-based hate speech. Through a detailed examination of human annotation results, we discuss the differences between Chinese and English hateful videos and underscore the importance of different modalities in hateful and offensive video analysis. Evaluations of state-of-the-art video classification models, such as VLM, GPT-4V and Qwen-VL, on MultiHateClip highlight the existing challenges in accurately distinguishing between hateful and offensive content and the urgent need for models that are both multimodally and culturally nuanced. MultiHateClip represents a foundational advance in enhancing hateful video detection by underscoring the necessity of a multimodal and culturally sensitive approach in combating online hate speech.