Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes them thematically, and uses these to enrich an outline into an abstractive summary. To personalize summaries, we introduce SCOPE, a reason-out-loud protocol that has the model build a reasoning trace by answering nine questions before content selection. For evaluation, we propose P-MESA, a multi-dimensional, reference-free evaluation framework to assess if a summary fits a target reader. P-MESA reliably identifies error instances, achieving >= 89% balanced accuracy against human annotations and strongly aligns with human severity ratings (r >= 0.70). On QMSum and FAME, FRAME reduces hallucination and omission by 2 out of 5 points (measured with MESA), while SCOPE improves knowledge fit and goal alignment over prompt-only baselines. Our findings advocate for rethinking summarization to improve control, faithfulness, and personalization.

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive speed-ups. Yet, current speculative decoding approaches remain limited by two fundamental bottlenecks: (1) the autoregressive dependency during drafting which limits parallelism, and (2) frequent rejections of draft tokens caused by misalignment between the draft and verify models. This paper proposes SpecDiff-2, a novel framework to jointly address these two bottlenecks. It leverages discrete diffusion as a non-autoregressive drafter to address bottleneck (1) and develops novel techniques to calibrate discrete diffusion drafters with autoregressive verifiers, addressing bottleneck (2). Experimental results across a comprehensive benchmark suite show that SpecDiff-2 achieves a new state-of-the-art across reasoning, coding, and mathematical benchmarks, improving tokens-per-second by up to an average of +55% over previous baselines and obtaining up to 5.5x average speed-up over standard decoding, without any loss of accuracy.

GEPOC, short for Generic Population Concept, is a collection of models and methods for analysing population-level research questions. For the valid application of the models for a specific country or region, stable and reproducible data processes are necessary, which provide valid and ready-to-use model parameters. This work contains a complete description of the data-processing methods for computation of model parameters for Austria, based exclusively on freely and publicly accessible data. In addition to the description of the source data used, this includes all algorithms used for aggregation, disaggregation, fusion, cleansing or scaling of the data, as well as a description of the resulting parameter files. The document places particular emphasis on the computation of parameters for the most important GEPOC model, GEPOC ABM, a continuous-time agent-based population model. An extensive validation study using this particular model was made and is presented at the end of this work.

Prior work has shown that two NLP evaluation experiments that report results for the same quality criterion name (e.g. Fluency) do not necessarily evaluate the same aspect of quality, and the comparability implied by the name can be misleading. Not knowing when two evaluations are comparable in this sense means we currently lack the ability to draw reliable conclusions about system quality on the basis of multiple, independently conducted evaluations. This in turn hampers the ability of the field to progress scientifically as a whole, a pervasive issue in NLP since its beginning (Sparck Jones, 1981). It is hard to see how the issue of unclear comparability can be fully addressed other than by the creation of a standard set of quality criterion names and definitions that the several hundred quality criterion names actually in use in the field can be mapped to, and grounded in. Taking a strictly descriptive approach, the QCET Quality Criteria for Evaluation Taxonomy derives a standard set of quality criterion names and definitions from three surveys of evaluations reported in NLP, and structures them into a hierarchy where each parent node captures common aspects of its child nodes. We present QCET and the resources it consists of, and discuss its three main uses in (i) establishing comparability of existing evaluations, (ii) guiding the design of new evaluations, and (iii) assessing regulatory compliance.

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method that makes the overclocking hyperparameter $α$ dynamic and context-aware. Our method adjusts reasoning speed in real time through two complementary signals: (1) token-level model uncertainty for fine-grained step-wise control, and (2) input complexity estimation for informed initialization. We implement this approach with three strategies: Uncertainty-Aware Alpha Scheduling (UA-$α$S), Complexity-Guided Alpha Initialization (CG-$α$I), and a Hybrid Adaptive Control (HAC) that combines both. Experiments on GSM8K, MATH, and SVAMP show that HAC achieves superior accuracy-latency trade-offs, reducing unnecessary computation on simple problems while allocating more resources to challenging ones. By mitigating overthinking, Adaptive Overclocking enhances both efficiency and overall reasoning performance.

Recently, Large Reasoning Models (LRMs) have gradually become a research hotspot due to their outstanding performance in handling complex tasks. Among them, DeepSeek R1 has garnered significant attention for its exceptional performance and open-source nature, driving advancements in the research of R1-style LRMs. Unlike traditional Large Language Models (LLMs), these models enhance logical deduction and decision-making capabilities during reasoning by incorporating mechanisms such as long chain-of-thought and self-reflection through reinforcement learning. However, with the widespread application of these models, the problem of overthinking has gradually emerged. Specifically, when generating answers, these models often construct excessively long reasoning chains with redundant or repetitive steps, which leads to reduced reasoning efficiency and may affect the accuracy of the final answer. To this end, various efficient reasoning methods have been proposed, aiming to reduce the length of reasoning paths without compromising model performance and reasoning capability. By reviewing the current research advancements in the field of efficient reasoning methods systematically, we categorize existing works into two main directions based on the lens of single-model optimization versus model collaboration: (1) Efficient Reasoning with Single Model, which focuses on improving the reasoning efficiency of individual models; and (2) Efficient Reasoning with Model Collaboration, which explores optimizing reasoning paths through collaboration among multiple models. Besides, we maintain a public GitHub repository that tracks the latest progress in efficient reasoning methods.

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek R1 have demonstrated impressive performance on complex reasoning tasks like mathematics and programming with long Chain-of-Thought (CoT) reasoning sequences (slow-thinking), compared with traditional large language models (fast-thinking). However, these reasoning models also face a huge challenge that generating unnecessarily lengthy and redundant reasoning chains even for trivial questions. This phenomenon leads to a significant waste of inference resources, increases the response time for simple queries, and hinders the practical application of LRMs in real-world products. To this end, it is crucial to shorten lengthy reasoning chains and learn adaptive reasoning between fast and slow thinking based on input difficulty. In this survey, we provide a comprehensive overview of recent progress in concise and adaptive thinking for efficient reasoning of LRMs, including methodologies, benchmarks, and challenges for future exploration. We hope this survey can help researchers quickly understand the landscape of this field and inspire novel adaptive thinking ideas to facilitate better usage of LRMs.

Understanding how policy language evolves over time is critical for assessing global responses to complex challenges such as climate change. Temporal analysis helps stakeholders, including policymakers and researchers, to evaluate past priorities, identify emerging themes, design governance strategies, and develop mitigation measures. Traditional approaches, such as manual thematic coding, are time-consuming and limited in capturing the complex, interconnected nature of global policy discourse. With the increasing relevance of unsupervised machine learning, these limitations can be addressed, particularly under high-volume, complex, and high-dimensional data conditions. In this work, we explore a novel approach that applies the dynamic embedded topic model (DETM) to analyze the evolution of global climate policy discourse. A probabilistic model designed to capture the temporal dynamics of topics over time. We collected a corpus of United Nations Framework Convention on Climate Change (UNFCCC) policy decisions from 1995 to 2023, excluding 2020 due to the postponement of COP26 as a result of the COVID-19 pandemic. The model reveals shifts from early emphases on greenhouse gases and international conventions to recent focuses on implementation, technical collaboration, capacity building, finance, and global agreements. Section 3 presents the modeling pipeline, including preprocessing, model training, and visualization of temporal word distributions. Our results show that DETM is a scalable and effective tool for analyzing the evolution of global policy discourse. Section 4 discusses the implications of these findings and we concluded with future directions and refinements to extend this approach to other policy domains.

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer quality in this setting is the length of the thinking stage. When the reasoning is too short, the model may fail to capture the complexity of the task. Conversely, when it is too long, the model may overthink, leading to unnecessary computation and degraded performance. This paper explores and exploits the underlying mechanisms by which LLMs understand and regulate the length of their reasoning during explicit thought processes. First, we show that LLMs encode their progress through the reasoning process and introduce an interactive progress bar visualization, which is then used to reveal insights on the model's planning dynamics. Second, we manipulate the internal progress encoding during inference to reduce unnecessary steps and generate a more concise and decisive chain of thoughts. Our empirical results demonstrate that this "overclocking" method mitigates overthinking, improves answer accuracy, and reduces inference latency. Our code is publicly available.

As large language models (LLMs) continue to evolve, questions about their trustworthiness in delivering factual information have become increasingly important. This concern also applies to their ability to accurately represent the geographic world. With recent advancements in this field, it is relevant to consider whether and to what extent LLMs' representations of the geographical world can be trusted. This study evaluates the performance of GPT-4o and Gemini 2.0 Flash in three key geospatial tasks: geocoding, elevation estimation, and reverse geocoding. In the geocoding task, both models exhibited systematic and random errors in estimating the coordinates of St. Anne's Column in Innsbruck, Austria, with GPT-4o showing greater deviations and Gemini 2.0 Flash demonstrating more precision but a significant systematic offset. For elevation estimation, both models tended to underestimate elevations across Austria, though they captured overall topographical trends, and Gemini 2.0 Flash performed better in eastern regions. The reverse geocoding task, which involved identifying Austrian federal states from coordinates, revealed that Gemini 2.0 Flash outperformed GPT-4o in overall accuracy and F1-scores, demonstrating better consistency across regions. Despite these findings, neither model achieved an accurate reconstruction of Austria's federal states, highlighting persistent misclassifications. The study concludes that while LLMs can approximate geographic information, their accuracy and reliability are inconsistent, underscoring the need for fine-tuning with geographical information to enhance their utility in GIScience and Geoinformatics.