Multi-Party Conversations (MPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets raise privacy concerns and often reflect platform-specific properties. For example, interactions between speakers may be limited due to rigid platform structures (e.g., threads, tree-like discussions), which yield overly simplistic interaction patterns (e.g., as a consequence of ``reply-to'' links). This work explores the feasibility of generating diverse MPCs with instruction-tuned Large Language Models (LLMs) by providing deterministic constraints such as dialogue structure and participants' stance. We investigate two complementary strategies of leveraging LLMs in this context: (i.) LLMs as MPC generators, where we task the LLM to generate a whole MPC at once and (ii.) LLMs as MPC parties, where the LLM generates one turn of the conversation at a time, provided the conversation history. We next introduce an analytical framework to evaluate compliance with the constraints, content quality, and interaction complexity for both strategies. Finally, we assess the quality of obtained MPCs via human annotation and LLM-as-a-judge evaluations. We find stark differences among LLMs, with only some being able to generate high-quality MPCs. We also find that turn-by-turn generation yields better conformance to constraints and higher linguistic variability than generating MPCs in one pass. Nonetheless, our structural and qualitative evaluation indicates that both generation strategies can yield high-quality MPCs.

Test-time compute scaling has emerged as a new axis along which to improve model accuracy, where additional computation is used at inference time to allow the model to think longer for more challenging problems. One promising approach for test-time compute scaling is search against a process reward model, where a model generates multiple potential candidates at each step of the search, and these partial trajectories are then scored by a separate reward model in order to guide the search process. The diversity of trajectories in the tree search process affects the accuracy of the search, since increasing diversity promotes more exploration. However, this diversity comes at a cost, as divergent trajectories have less KV sharing, which means they consume more memory and slow down the search process. Previous search methods either do not perform sufficient exploration, or else explore diverse trajectories but have high latency. We address this challenge by proposing Efficient Tree Search (ETS), which promotes KV sharing by pruning redundant trajectories while maintaining necessary diverse trajectories. ETS incorporates a linear programming cost model to promote KV cache sharing by penalizing the number of nodes retained, while incorporating a semantic coverage term into the cost model to ensure that we retain trajectories which are semantically different. We demonstrate how ETS can achieve 1.8$\times$ reduction in average KV cache size during the search process, leading to 1.4$\times$ increased throughput relative to prior state-of-the-art methods, with minimal accuracy degradation and without requiring any custom kernel implementation. Code is available at: https://github.com/SqueezeAILab/ETS.

This paper addresses the critical need for detecting bias in government documents, an underexplored area with significant implications for governance. Existing methodologies often overlook the unique context and far-reaching impacts of governmental documents, potentially obscuring embedded biases that shape public policy and citizen-government interactions. To bridge this gap, we introduce the Dutch Government Data for Bias Detection (DGDB), a dataset sourced from the Dutch House of Representatives and annotated for bias by experts. We fine-tune several BERT-based models on this dataset and compare their performance with that of generative language models. Additionally, we conduct a comprehensive error analysis that includes explanations of the models' predictions. Our findings demonstrate that fine-tuned models achieve strong performance and significantly outperform generative language models, indicating the effectiveness of DGDB for bias detection. This work underscores the importance of labeled datasets for bias detection in various languages and contributes to more equitable governance practices.

Marine heatwaves (MHWs) are extreme ocean-temperature events with significant impacts on marine ecosystems and related industries. Accurate forecasts (one to six months ahead) of MHWs would aid in mitigating these impacts. However, forecasting MHWs presents a challenging imbalanced regression task due to the rarity of extreme temperature anomalies in comparison to more frequent moderate conditions. In this study, we examine monthly MHW forecasts for 12 locations around New Zealand. We use a fully-connected neural network and compare standard and specialized regression loss functions, including the mean squared error (MSE), the mean absolute error (MAE), the Huber, the weighted MSE, the focal-R, the balanced MSE, and a proposed scaling-weighted MSE. Results show that (i) short lead times (one month) are considerably more predictable than three- and six-month leads, (ii) models trained with the standard MSE or MAE losses excel at forecasting average conditions but struggle to capture extremes, and (iii) specialized loss functions such as the balanced MSE and our scaling-weighted MSE substantially improve forecasting of MHW and suspected MHW events. These findings underscore the importance of tailored loss functions for imbalanced regression, particularly in forecasting rare but impactful events such as MHWs.

We show how to add and eliminate binary preference on plays in Alternating-time Temporal Logic (ATL) with strategy contexts on Concurrent Game Models (CGMs) by means of a translation which preserves satisfaction in models where preference-indiscernibility between plays is an equivalence relation of finite index. The elimination technique also works for a companion second-order path quantifier, which makes quantified path variables range over sets of plays that are closed under preference-indiscernibility. We argue that the preference operator and the specialized quantifier facilitate formulating interesting solution concepts such as Nash equilibrium and secure equilibrium in a straightforward way. We also present a novel translation from ATL with strategy contexts to Quantified Computation Tree Logic (QCTL). Together with the translation which eliminates preference and the specialized form of quantification, this translation allows reasoning about infinite multiplayer synchronous games on CGMs to be translated from the proposed extension of ATL with strategy contexts into QCTL. The setting is related to that of ordered objectives in the works of Bouyer, Brenguier, Markey and Ummels, except that our focus is on the use of the temporal logic languages mentioned above, and we rely on translations into QCTL for the algorithmic solutions.

Recent advancement in machine learning algorithms reaches a point where medical devices can be equipped with artificial intelligence (AI) models for diagnostic support and routine automation in clinical settings. In medicine and healthcare, there is a particular demand for sufficient and objective explainability of the outcome generated by AI models. However, AI models are generally considered as black boxes due to their complexity, and the computational process leading to their response is often opaque. Although several methods have been proposed to explain the behavior of models by evaluating the importance of each feature in discrimination and prediction, they may suffer from biases and opacities arising from the scale and sampling protocol of the dataset used for training or testing. To overcome the shortcomings of existing methods, we explore an alternative approach to provide an objective explanation of AI models that can be defined independently of the learning process and does not require additional data. As a preliminary study for this direction of research, this work examines a numerical availability of the Jacobian matrix of deep learning models that measures how stably a model responses against small perturbations added to the input. The indicator, if available, are calculated from a trained AI model for a given target input. This is a first step towards a perturbation-based explanation, which will assist medical practitioners in understanding and interpreting the response of the AI model in its clinical application.

Ukraine and Russia are now three years into what has been called the first drone war: not the first in which they were used, but the first in which they have been a major factor on the battlefield. What lessons have others drawn about the shape of future wars? "Drones are here to stay, and they will be everywhere – on the ground, in the air and at sea – in numbers," says Oleksandra Molloy at the University of New South Wales in Canberra, Australia. "The point of no return was…

AI systems often exhibit political bias, influencing users' opinions and decision-making. While political neutrality-defined as the absence of bias-is often seen as an ideal solution for fairness and safety, this position paper argues that true political neutrality is neither feasible nor universally desirable due to its subjective nature and the biases inherent in AI training data, algorithms, and user interactions. However, inspired by Joseph Raz's philosophical insight that "neutrality [...] can be a matter of degree" (Raz, 1986), we argue that striving for some neutrality remains essential for promoting balanced AI interactions and mitigating user manipulation. Therefore, we use the term "approximation" of political neutrality to shift the focus from unattainable absolutes to achievable, practical proxies. We propose eight techniques for approximating neutrality across three levels of conceptualizing AI, examining their trade-offs and implementation strategies. In addition, we explore two concrete applications of these approximations to illustrate their practicality. Finally, we assess our framework on current large language models (LLMs) at the output level, providing a demonstration of how it can be evaluated. This work seeks to advance nuanced discussions of political neutrality in AI and promote the development of responsible, aligned language models.

Throughout this project, we have attempted to develop an automatic evaluator that determines whether Basque language compositions meet the C1 level. To achieve our goal, we obtained 10,000 transcribed compositions through an agreement between HABE and HiTZ to train our system. We have developed different techniques to avoid data scarcity and system overfitting: EDA, SCL and regulation; We have also conducted tests with different Language Models to analyze their behavior. Finally, we have also performed analyses of different system behaviors to measure model calibration and the impact of artifacts. -- Proiektu honetan zehar euskarazko idazlanek C1 maila duten edo ez zehazten duen ebaluatzaile automatiko bat garatzen saiatu gara. Gure helburua betetzeko HABE eta HiTZ arteko hitzarmenaren bitartez 10.000 transkribatutako idazlan eskuratu ditugu gure sistema entrenatzeko. Datu eskasia eta sistemaren gaindoitzea ekiditeko teknika ezberdinak landu ditugu: EDA, SCL eta erregulazioa; Hizkuntza Eredu ezberdinekin ere probak egin ditugu duten portaera aztertzeko. Azkenik, sistema ezberdinen portaeren analisiak ere egin ditugu, ereduen kalibrazioa eta artefaktuen eragina neurtzeko.

Abstract--Large language models (LLMs) face the challenge of hallucinations - outputs that seem coherent but are actually incorrect. A particularly damaging type is fact-conflicting hallucination (FCH), where generated content contradicts established facts. Addressing FCH presents three main challenges: 1) Automatically constructing and maintaining large-scale benchmark datasets is difficult and resource-intensive; 2) Generating complex and efficient test cases that the LLM has not been trained on - especially those involving intricate temporal features - is challenging, yet crucial for eliciting hallucinations; and 3) Validating the reasoning behind LLM outputs is inherently difficult, particularly with complex logical relationships, as it requires transparency in the model's decision-making process. LLMs are tested using these cases through template-based prompts, which require them to generate both answers and reasoning steps. T o validate the reasoning, we propose two semantic-aware oracles that compare the semantic structure of LLM outputs to the ground truths. Key insights reveal that LLMs struggle with out-of-distribution knowledge and logical reasoning. These findings highlight the importance of continued efforts to detect and mitigate hallucinations in LLMs. Large Language Models (LLMs) have revolutionized language processing, demonstrating impressive text generation and comprehension capabilities with diverse applications. However, despite their growing use, LLMs face significant security and privacy challenges [1], [2], [3], [4], [5], which affect their overall effectiveness and reliability . A critical issue is the phenomenon of hallucination, where LLMs generate outputs that are coherent but factually incorrect or irrelevant. This tendency to produce misleading information compromises the safety and usability of LLM-based systems. This paper focuses on fact-conflicting hallucina tion (FCH), the most prominent form of hallucination in LLMs. FCH occurs when LLMs generate content that directly contradicts established facts. For instance, as illustrated in Figure 1, an LLM incorrectly asserts that " Haruki Murakami won the Nobel Prize in Literature in 2016 ", whereas the fact is that "Haruki Murakami has not won the Nobel Prize, though he has received numerous other literary awards ". Such inaccuracies can significantly lead to user confusion and undermine the trust and reliability that are crucial for LLM applications. N. Li, K. Wang, and H. Wang are with Huazhong University of Science and T echnology, China. Song is with the National University of Singapore, Singapore. Li is with the University of New South Wales, Australia.