"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions

Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access to psychosocial support. Peer support, grounded in lived experience, offers a valuable complement to professional care. However, variability in training, effectiveness, and definitions raises concerns about quality, consistency, and safety. Large Language Models (LLMs) present new opportunities to enhance peer support interactions, particularly in real-time, text-based interactions. We present and evaluate an AI-supported system with an LLM-simulated distressed client, context-sensitive LLM-generated suggestions, and real-time emotion visualisations. 2 mixed-methods studies with 12 peer supporters and 5 mental health professionals (i.e., experts) examined the system's effectiveness and implications for practice. Both groups recognised its potential to enhance training and improve interaction quality. However, we found a key tension emerged: while peer supporters engaged meaningfully, experts consistently flagged critical issues in peer supporter responses, such as missed distress cues and premature advice-giving. This misalignment highlights potential limitations in current peer support training, especially in emotionally charged contexts where safety and fidelity to best practices are essential. Our findings underscore the need for standardised, psychologically grounded training, especially as peer support scales globally. They also demonstrate how LLM-supported systems can scaffold this development--if designed with care and guided by expert oversight. This work contributes to emerging conversations on responsible AI integration in mental health and the evolving role of LLMs in augmenting peer-delivered care.

Sword and Shield: Uses and Strategies of LLMs in Navigating Disinformation

The emergence of Large Language Models (LLMs) presents a dual challenge in the fight against disinformation. These powerful tools, capable of generating human-like text at scale, can be weaponised to produce sophisticated and persuasive disinformation, yet they also hold promise for enhancing detection and mitigation strategies. This paper investigates the complex dynamics between LLMs and disinformation through a communication game that simulates online forums, inspired by the game Werewolf, with 25 participants. We analyse how Disinformers, Moderators, and Users leverage LLMs to advance their goals, revealing both the potential for misuse and combating disinformation. Our findings highlight the varying uses of LLMs depending on the participants' roles and strategies, underscoring the importance of understanding their effectiveness in this context. We conclude by discussing implications for future LLM development and online platform design, advocating for a balanced approach that empowers users and fosters trust while mitigating the risks of LLM-assisted disinformation.

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these limitations, we propose SuperWriter-Agent, an agent-based framework designed to enhance the quality and consistency of long-form text generation. SuperWriter-Agent introduces explicit structured thinking-through planning and refinement stages into the generation pipeline, guiding the model to follow a more deliberate and cognitively grounded process akin to that of a professional writer. Based on this framework, we construct a supervised fine-tuning dataset to train a 7B SuperWriter-LM. We further develop a hierarchical Direct Preference Optimization (DPO) procedure that uses Monte Carlo Tree Search (MCTS) to propagate final quality assessments and optimize each generation step accordingly. Empirical results across diverse benchmarks demonstrate that SuperWriter-LM achieves state-of-the-art performance, surpassing even larger-scale baseline models in both automatic evaluation and human evaluation. Furthermore, comprehensive ablation studies demonstrate the effectiveness of hierarchical DPO and underscore the value of incorporating structured thinking steps to improve the quality of long-form text generation.

Understanding Refusal in Language Models with Sparse Autoencoders

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify latent features that causally mediate refusal behaviors. We apply our method to two open-source chat models and intervene on refusal-related features to assess their influence on generation, validating their behavioral impact across multiple harmful datasets. This enables a fine-grained inspection of how refusal manifests at the activation level and addresses key research questions such as investigating upstream-downstream latent relationship and understanding the mechanisms of adversarial jailbreaking techniques. We also establish the usefulness of refusal features in enhancing generalization for linear probes to out-of-distribution adversarial samples in classification tasks. We open source our code in https://github.com/wj210/refusal_sae.

Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs

Large Language Models (LLMs) augmented with retrieval mechanisms have demonstrated significant potential in fact-checking tasks by integrating external knowledge. However, their reliability decreases when confronted with conflicting evidence from sources of varying credibility. This paper presents the first systematic evaluation of Retrieval-Augmented Generation (RAG) models for fact-checking in the presence of conflicting evidence. To support this study, we introduce \textbf{CONFACT} (\textbf{Con}flicting Evidence for \textbf{Fact}-Checking) (Dataset available at https://github.com/zoeyyes/CONFACT), a novel dataset comprising questions paired with conflicting information from various sources. Extensive experiments reveal critical vulnerabilities in state-of-the-art RAG methods, particularly in resolving conflicts stemming from differences in media source credibility. To address these challenges, we investigate strategies to integrate media background information into both the retrieval and generation stages. Our results show that effectively incorporating source credibility significantly enhances the ability of RAG models to resolve conflicting evidence and improve fact-checking performance.

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.