The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights that are later reflected in the outputs of the model is challenging. In this study we propose a strategy to finetune a pair of low-rank adapters of a model, one serving as the text-generating model, and the other as the detector, so that a subtle watermark is embedded into the text generated by the first model and simultaneously optimized for detectability by the second. In this way, the watermarking strategy is fully learned end-to-end. This process imposes an optimization challenge, as balancing watermark robustness, naturalness, and task performance requires trade-offs. We discuss strategies on how to optimize this min-max objective and present results showing the effect of this modification to instruction finetuning.

Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises-claims that contradict established facts. Such premises can mislead LLMs into offering fabricated or misleading details. Existing approaches include pretraining, fine-tuning, and inference-time techniques that often rely on access to logits or address hallucinations after they occur. These methods tend to be computationally expensive, require extensive training data, or lack proactive mechanisms to prevent hallucination before generation, limiting their efficiency in real-time applications. We propose a retrieval-based framework that identifies and addresses false premises before generation. Our method first transforms a user's query into a logical representation, then applies retrieval-augmented generation (RAG) to assess the validity of each premise using factual sources. Finally, we incorporate the verification results into the LLM's prompt to maintain factual consistency in the final output. Experiments show that this approach effectively reduces hallucinations, improves factual accuracy, and does not require access to model logits or large-scale fine-tuning.

As leading examples of large language models, ChatGPT and Gemini claim to provide accurate and unbiased information, emphasizing their commitment to political neutrality and avoidance of personal bias. This research investigates the political tendency of large language models and the existence of differentiation according to the query language. For this purpose, ChatGPT and Gemini were subjected to a political axis test using 14 different languages. The findings of the study suggest that these large language models do exhibit political tendencies, with both models demonstrating liberal and leftist biases. A comparative analysis revealed that Gemini exhibited a more pronounced liberal and left-wing tendency compared to ChatGPT. The study also found that these political biases varied depending on the language used for inquiry. The study delves into the factors that constitute political tendencies and linguistic differentiation, exploring differences in the sources and scope of educational data, structural and grammatical features of languages, cultural and political contexts, and the model's response to linguistic features. From this standpoint, and an ethical perspective, it is proposed that artificial intelligence tools should refrain from asserting a lack of political tendencies and neutrality, instead striving for political neutrality and executing user queries by incorporating these tendencies.

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes. Recent work shows that SD can accelerate decoding with large batch sizes too if the context is sufficiently long and the draft model's KV cache is sparse. We introduce SPIRe, a draft model that combines static sparse attention, pruned initialization, and feedback memory to increase the modeled throughput of speculative decoding by over 100% compared to speculation with a much smaller draft model and by over 35% compared to the strong baseline of sparse self-speculation. Our approach is particularly effective when context lengths vary significantly across requests.

Sensory language expresses embodied experiences ranging from taste and sound to excitement and stomachache. This language is of interest to scholars from a wide range of domains including robotics, narratology, linguistics, and cognitive science. In this work, we explore whether language models, which are not embodied, can approximate human use of embodied language. We extend an existing corpus of parallel human and model responses to short story prompts with an additional 18,000 stories generated by 18 popular models. We find that all models generate stories that differ significantly from human usage of sensory language, but the direction of these differences varies considerably between model families. Namely, Gemini models use significantly more sensory language than humans along most axes whereas most models from the remaining five families use significantly less. Linear probes run on five models suggest that they are capable of identifying sensory language. However, we find preliminary evidence suggesting that instruction tuning may discourage usage of sensory language. Finally, to support further work, we release our expanded story dataset.

Query understanding in Conversational Information Seeking (CIS) involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. Large Language Models (LLMs) enhance this process by interpreting nuanced language and adapting dynamically, improving the relevance and precision of search results in real-time. In this tutorial, we explore advanced techniques to enhance query understanding in LLM-based CIS systems. We delve into LLM-driven methods for developing robust evaluation metrics to assess query understanding quality in multi-turn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We also discuss key challenges in integrating LLMs for query understanding in conversational search systems and outline future research directions. Our goal is to deepen the audience's understanding of LLM-based conversational query understanding and inspire discussions to drive ongoing advancements in this field.

Geometric Machine Learning (GML) has shown that respecting non-Euclidean geometry in data spaces can significantly improve performance over naive Euclidean assumptions. In parallel, Quantum Machine Learning (QML) has emerged as a promising paradigm that leverages superposition, entanglement, and interference within quantum state manifolds for learning tasks. This paper offers a unifying perspective by casting QML as a specialized yet more expressive branch of GML. We argue that quantum states, whether pure or mixed, reside on curved manifolds (e.g., projective Hilbert spaces or density-operator manifolds), mirroring how covariance matrices inhabit the manifold of symmetric positive definite (SPD) matrices or how image sets occupy Grassmann manifolds. However, QML also benefits from purely quantum properties, such as entanglement-induced curvature, that can yield richer kernel structures and more nuanced data embeddings. We illustrate these ideas with published and newly discussed results, including hybrid classical -quantum pipelines for diabetic foot ulcer classification and structural health monitoring. Despite near-term hardware limitations that constrain purely quantum solutions, hybrid architectures already demonstrate tangible benefits by combining classical manifold-based feature extraction with quantum embeddings. We present a detailed mathematical treatment of the geometrical underpinnings of quantum states, emphasizing parallels to classical Riemannian geometry and manifold-based optimization. Finally, we outline open research challenges and future directions, including Quantum Large Language Models (LLMs), quantum reinforcement learning, and emerging hardware approaches, demonstrating how synergizing GML and QML principles can unlock the next generation of machine intelligence.

As large language models (LLMs) increasingly integrate into our daily lives, it becomes crucial to understand their implicit biases and moral tendencies. To address this, we introduce a Moral Foundations LLM dataset (MFD-LLM) grounded in Moral Foundations Theory, which conceptualizes human morality through six core foundations. We propose a novel evaluation method that captures the full spectrum of LLMs' revealed moral preferences by answering a range of real-world moral dilemmas. Our findings reveal that state-of-the-art models have remarkably homogeneous value preferences, yet demonstrate a lack of consistency.

Formulating research questions is a foundational yet challenging academic skill, one that generative AI systems often oversimplify by offering instant answers at the expense of student reflection. This protocol lays out a study grounded in constructivist learning theory to evaluate a novel AI-based Socratic Tutor, designed to foster cognitive engagement and scaffold research question development in higher education. Anchored in dialogic pedagogy, the tutor engages students through iterative, reflective questioning, aiming to promote System 2 thinking and counteract overreliance on AI-generated outputs. In a quasi-experimental design, approximately 80 German pre-service biology teacher students will be randomly assigned to one of two groups: an AI Socratic Tutor condition and an uninstructed chatbot control. Across multiple cycles, students are expected to formulate research questions based on background texts, with quality assessed through double-blind expert review. The study also examines transfer of skills to novel phenomena and captures student perceptions through mixed-methods analysis, including surveys, interviews and reflective journals. This study aims to advance the understanding of how generative AI can be pedagogically aligned to support, not replace, human cognition and offers design principles for human-AI collaboration in education.

Recent advancements in generative AI have significantly increased interest in personalized agents. With increased personalization, there is also a greater need for being able to trust decision-making and action taking capabilities of these agents. However, the evaluation methods for these agents remain outdated and inadequate, often failing to capture the dynamic and evolving nature of user interactions. In this conceptual article, we argue for a paradigm shift in evaluating personalized and adaptive agents. We propose a comprehensive novel framework that models user personas with unique attributes and preferences. In this framework, agents interact with these simulated users through structured interviews to gather their preferences and offer customized recommendations. These recommendations are then assessed dynamically using simulations driven by Large Language Models (LLMs), enabling an adaptive and iterative evaluation process. Our flexible framework is designed to support a variety of agents and applications, ensuring a comprehensive and versatile evaluation of recommendation strategies that focus on proactive, personalized, and trustworthy aspects.