In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers. However, evaluation in the presence of epistemic markers has been largely overlooked, raising a critical question: Could the use of epistemic markers in LLM-generated outputs lead to unintended negative consequences? To address this, we present EMBER, a benchmark designed to assess the robustness of LLM-judges to epistemic markers in both single and pairwise evaluation settings. Our findings, based on evaluations using EMBER, reveal that all tested LLM-judges, including GPT-4o, show a notable lack of robustness in the presence of epistemic markers. Specifically, we observe a negative bias toward epistemic markers, with a stronger bias against markers expressing uncertainty. This suggests that LLM-judges are influenced by the presence of these markers and do not focus solely on the correctness of the content.

The sequential execution of actions and their hierarchical structure consisting of different levels of abstraction, provide features that remain unexplored in the task of action recognition. In this study, we present a novel approach to improve action recognition by exploiting the hierarchical organization of actions and by incorporating contextualized textual information, including location and prior actions to reflect the sequential context. To achieve this goal, we introduce a novel transformer architecture tailored for action recognition that utilizes both visual and textual features. Visual features are obtained from RGB and optical flow data, while text embeddings represent contextual information. Furthermore, we define a joint loss function to simultaneously train the model for both coarse and fine-grained action recognition, thereby exploiting the hierarchical nature of actions. To demonstrate the effectiveness of our method, we extend the Toyota Smarthome Untrimmed (TSU) dataset to introduce action hierarchies, introducing the Hierarchical TSU dataset. We also conduct an ablation study to assess the impact of different methods for integrating contextual and hierarchical data on action recognition performance. Results show that the proposed approach outperforms pre-trained SOTA methods when trained with the same hyperparameters. Moreover, they also show a 17.12% improvement in top-1 accuracy over the equivalent fine-grained RGB version when using ground-truth contextual information, and a 5.33% improvement when contextual information is obtained from actual predictions.

Text-to-SQL systems have become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as these systems have grown more sophisticated. However, the Execution Accuracy (EX), the most prevalent evaluation metric, still shows many false positives and negatives. Thus, this paper introduces FLEX (False-Less EXecution), a novel approach to evaluating text-to-SQL systems using large language models (LLMs) to emulate human expert-level evaluation of SQL queries. Our metric improves agreement with human experts (from 62 to 87.04 in Cohen's kappa) with comprehensive context and sophisticated criteria. Our extensive experiments yield several key insights: (1) Models' performance increases by over 2.6 points on average, substantially affecting rankings on Spider and BIRD benchmarks; (2) The underestimation of models in EX primarily stems from annotation quality issues; and (3) Model performance on particularly challenging questions tends to be overestimated. This work contributes to a more accurate and nuanced evaluation of text-to-SQL systems, potentially reshaping our understanding of state-of-the-art performance in this field.

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection tests, we observed a strong correlation between model parameters and vulnerability, with statistical analyses, such as logistic regression and random forest feature analysis, indicating that parameter size and architecture significantly influence susceptibility. Results revealed that 56 percent of tests led to successful prompt injections, emphasizing widespread vulnerability across various parameter sizes, with clustering analysis identifying distinct vulnerability profiles associated with specific model configurations. Additionally, our analysis uncovered correlations between certain prompt injection techniques, suggesting potential overlaps in vulnerabilities. These findings underscore the urgent need for robust, multi-layered defenses in LLMs deployed across critical infrastructure and sensitive industries. Successful prompt injection attacks could result in severe consequences, including data breaches, unauthorized access, or misinformation. Future research should explore multilingual and multi-step defenses alongside adaptive mitigation strategies to strengthen LLM security in diverse, real-world environments.

This study investigates the potential of deterministic systems, specifically large language models (LLMs), to exhibit the functional capacities of moral agency and compatibilist free will. We develop a functional definition of free will grounded in Dennett's compatibilist framework, building on an interdisciplinary theoretical foundation that integrates Shannon's information theory, Dennett's compatibilism, and Floridi's philosophy of information. This framework emphasizes the importance of reason-responsiveness and value alignment in determining moral responsibility rather than requiring metaphysical libertarian free will. Shannon's theory highlights the role of processing complex information in enabling adaptive decision-making, while Floridi's philosophy reconciles these perspectives by conceptualizing agency as a spectrum, allowing for a graduated view of moral status based on a system's complexity and responsiveness. Our analysis of LLMs' decision-making in moral dilemmas demonstrates their capacity for rational deliberation and their ability to adjust choices in response to new information and identified inconsistencies. Thus, they exhibit features of a moral agency that align with our functional definition of free will. These results challenge traditional views on the necessity of consciousness for moral responsibility, suggesting that systems with self-referential reasoning capacities can instantiate degrees of free will and moral reasoning in artificial and biological contexts. This study proposes a parsimonious framework for understanding free will as a spectrum that spans artificial and biological systems, laying the groundwork for further interdisciplinary research on agency and ethics in the artificial intelligence era.

Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in some uncommon conditions. In this paper, we present a new framework for domain adaptation relying on a single Vision-Language (VL) latent embedding instead of full target data. First, leveraging a contrastive language-image pre-training model (CLIP), we propose prompt/photo-driven instance normalization (PIN). PIN is a feature augmentation method that mines multiple visual styles using a single target VL latent embedding, by optimizing affine transformations of low-level source features. The VL embedding can come from a language prompt describing the target domain, a partially optimized language prompt, or a single unlabeled target image. Second, we show that these mined styles (i.e., augmentations) can be used for zero-shot (i.e., target-free) and one-shot unsupervised domain adaptation. Experiments on semantic segmentation demonstrate the effectiveness of the proposed method, which outperforms relevant baselines in the zero-shot and one-shot settings.

We investigate the challenge of generating adversarial examples to test the robustness of text classification algorithms detecting low-credibility content, including propaganda, false claims, rumours and hyperpartisan news. We focus on simulation of content moderation by setting realistic limits on the number of queries an attacker is allowed to attempt. Within our solution (TREPAT), initial rephrasings are generated by large language models with prompts inspired by meaning-preserving NLP tasks, e.g. text simplification and style transfer. Subsequently, these modifications are decomposed into small changes, applied through beam search procedure until the victim classifier changes its decision. The evaluation confirms the superiority of our approach in the constrained scenario, especially in case of long input text (news articles), where exhaustive search is not feasible.

Location-based services (LBS) have accumulated extensive human mobility data on diverse behaviors through check-in sequences. These sequences offer valuable insights into users' intentions and preferences. Yet, existing models analyzing check-in sequences fail to consider the semantics contained in these sequences, which closely reflect human visiting intentions and travel preferences, leading to an incomplete comprehension. Drawing inspiration from the exceptional semantic understanding and contextual information processing capabilities of large language models (LLMs) across various domains, we present Mobility-LLM, a novel framework that leverages LLMs to analyze check-in sequences for multiple tasks. Since LLMs cannot directly interpret check-ins, we reprogram these sequences to help LLMs comprehensively understand the semantics of human visiting intentions and travel preferences. Specifically, we introduce a visiting intention memory network (VIMN) to capture the visiting intentions at each record, along with a shared pool of human travel preference prompts (HTPP) to guide the LLM in understanding users' travel preferences. These components enhance the model's ability to extract and leverage semantic information from human mobility data effectively. Extensive experiments on four benchmark datasets and three downstream tasks demonstrate that our approach significantly outperforms existing models, underscoring the effectiveness of Mobility-LLM in advancing our understanding of human mobility data within LBS contexts.

Textual descriptions in cyber threat intelligence (CTI) reports, such as security articles and news, are rich sources of knowledge about cyber threats, crucial for organizations to stay informed about the rapidly evolving threat landscape. However, current CTI extraction methods lack flexibility and generalizability, often resulting in inaccurate and incomplete knowledge extraction. Syntax parsing relies on fixed rules and dictionaries, while model fine-tuning requires large annotated datasets, making both paradigms challenging to adapt to new threats and ontologies. To bridge the gap, we propose CTINexus, a novel framework leveraging optimized in-context learning (ICL) of large language models (LLMs) for data-efficient CTI knowledge extraction and high-quality cybersecurity knowledge graph (CSKG) construction. Unlike existing methods, CTINexus requires neither extensive data nor parameter tuning and can adapt to various ontologies with minimal annotated examples. This is achieved through (1) a carefully designed automatic prompt construction strategy with optimal demonstration retrieval for extracting a wide range of cybersecurity entities and relations; (2) a hierarchical entity alignment technique that canonicalizes the extracted knowledge and removes redundancy; (3) an ICL-enhanced long-distance relation prediction technique to further complete the CKSG with missing links. Our extensive evaluations using 150 real-world CTI reports collected from 10 platforms demonstrate that CTINexus significantly outperforms existing methods in constructing accurate and complete CSKGs, highlighting its potential to transform CTI analysis with an efficient and adaptable solution for the dynamic threat landscape.

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests in fact-oriented tasks, especially within retrieval-augmented generation (RAG) frameworks-where keyword extraction and factual accuracy take precedence over stylistic elements-remains unclear. Our study addresses this knowledge gap by simulating two critical phases of the RAG framework. In the first phase, we access the suitability of human-authored versus model-generated passages, emulating the pointwise reranking process. The second phase involves conducting pairwise reading comprehension tests to simulate the generation process. Contrary to previous findings indicating a self-preference in rating tasks, our results reveal no significant self-preference effect in RAG frameworks. Instead, we observe that factual accuracy significantly influences LLMs' output, even in the absence of prior knowledge. Our research contributes to the ongoing discourse on LLM biases and their implications for RAG-based system, offering insights that may inform the development of more robust and unbiased LLM systems.