There is a surge observed in research and applications of computer science and artificial intelligence in the legal domain. The related term computational law is commonly defined as "the branch of Legal Informatics concerned with the representation of rule and regulations in computable form" [Genesereth and Chaudhri, 2022]. The focus of an important percentage of related work on computational law is on automatic processing, generation, or understanding of legal documents [Küçük and Can, 2024]. Recent advancements in artificial intelligence (AI), such as generative AI models, pre-trained language models (PLMs) or large language models (LLMs), and chatbots developed using such models, have also affected the domain of computational law, and this dramatic impact is also acknowledged by legal professionals [Goth, 2024]. Undoubtedly, annotated or unannotated datasets and benchmarks in digital form are required for legal AI studies on legal texts, in order to facilitate model training, and to ensure sound comparisons of different approaches to the problems pertaining to computational law.

Reasoning ability is crucial for solving challenging tasks. With the advancement of foundation models, such as the emergence of large language models (LLMs), a wide range of reasoning strategies has been proposed, including test-time enhancements, such as Chain-ofThought, and post-training optimizations, as used in DeepSeek-R1. While these reasoning strategies have demonstrated effectiveness across various challenging language or vision tasks, their applicability and impact on time-series forecasting (TSF), particularly the challenging zero-shot TSF, remain largely unexplored. In particular, it is unclear whether zero-shot TSF benefits from reasoning and, if so, what types of reasoning strategies are most effective. To bridge this gap, we propose ReC4TS, the first benchmark that systematically evaluates the effectiveness of popular reasoning strategies when applied to zero-shot TSF tasks. ReC4TS conducts comprehensive evaluations across datasets spanning eight domains, covering both unimodal and multimodal with short-term and longterm forecasting tasks. More importantly, ReC4TS provides key insights: (1) Self-consistency emerges as the most effective test-time reasoning strategy; (2) Group-relative policy optimization emerges as a more suitable approach for incentivizing reasoning ability during post-training; (3) Multimodal TSF benefits more from reasoning strategies compared to unimodal TSF. Beyond these insights, ReC4TS establishes two pioneering starting blocks to support future zero-shot TSF reasoning research: (1) A novel dataset, TimeThinking, containing forecasting samples annotated with reasoning trajectories from multiple advanced LLMs, and (2) A new and simple test-time scaling-law validated on foundational TSF models enabled by self-consistency reasoning strategy. All data and code are publicly accessible at: https://github.com/AdityaLab/OpenTimeR

Recent advances in test-time scaling have shown promising results in improving Large Language Models (LLMs) performance through strategic computation allocation during inference. While this approach has demonstrated strong performance improvements in logical and mathematical reasoning tasks, its application to natural language generation (NLG), especially summarization, has yet to be explored. Multi-Document Summarization (MDS) is a challenging task that focuses on extracting and synthesizing useful information from multiple lengthy documents. Unlike reasoning tasks, MDS requires a more nuanced approach to prompt design and ensemble, as there is no "best" prompt to satisfy diverse summarization requirements. To address this, we propose a novel framework that leverages inference-time scaling for this task. Precisely, we take prompt ensemble approach by leveraging various prompt to first generate candidate summaries and then ensemble them with an aggregator to produce a refined summary. We also introduce two new evaluation metrics: Consistency-Aware Preference (CAP) score and LLM Atom-Content-Unit (ACU) score, to enhance LLM's contextual understanding while mitigating its positional bias. Extensive experiments demonstrate the effectiveness of our approach in improving summary quality while identifying and analyzing the scaling boundaries in summarization tasks.

Strategic decision-making involves interactive reasoning where agents adapt their choices in response to others, yet existing evaluations of large language models (LLMs) often emphasize Nash Equilibrium (NE) approximation, overlooking the mechanisms driving their strategic choices. To bridge this gap, we introduce an evaluation framework grounded in behavioral game theory, disentangling reasoning capability from contextual effects. Testing 22 state-of-the-art LLMs, we find that GPT-o3-mini, GPT-o1, and DeepSeek-R1 dominate most games yet also demonstrate that the model scale alone does not determine performance. In terms of prompting enhancement, Chain-of-Thought (CoT) prompting is not universally effective, as it increases strategic reasoning only for models at certain levels while providing limited gains elsewhere. Additionally, we investigate the impact of encoded demographic features on the models, observing that certain assignments impact the decision-making pattern. For instance, GPT-4o shows stronger strategic reasoning with female traits than males, while Gemma assigns higher reasoning levels to heterosexual identities compared to other sexual orientations, indicating inherent biases. These findings underscore the need for ethical standards and contextual alignment to balance improved reasoning with fairness.

The performance emergence of large language models (LLMs) driven by data scaling laws makes the selection of pre-training data increasingly important. However, existing methods rely on limited heuristics and human intuition, lacking comprehensive and clear guidelines. To address this, we are inspired by ``reverse thinking'' -- prompting LLMs to self-identify which criteria benefit its performance. As its pre-training capabilities are related to perplexity (PPL), we derive 14 quality criteria from the causes of text perplexity anomalies and introduce 15 common application domains to support domain mixing. In this paper, we train a Data Manager (DataMan) to learn quality ratings and domain recognition from pointwise rating, and use it to annotate a 447B token pre-training corpus with 14 quality ratings and domain type. Our experiments validate our approach, using DataMan to select 30B tokens to train a 1.3B-parameter language model, demonstrating significant improvements in in-context learning (ICL), perplexity, and instruction-following ability over the state-of-the-art baseline. The best-performing model, based on the Overall Score l=5 surpasses a model trained with 50% more data using uniform sampling. We continue pre-training with high-rated, domain-specific data annotated by DataMan to enhance domain-specific ICL performance and thus verify DataMan's domain mixing ability. Our findings emphasize the importance of quality ranking, the complementary nature of quality criteria, and their low correlation with perplexity, analyzing misalignment between PPL and ICL performance. We also thoroughly analyzed our pre-training dataset, examining its composition, the distribution of quality ratings, and the original document sources.

Text summarization plays a crucial role in natural language processing by condensing large volumes of text into concise and coherent summaries. As digital content continues to grow rapidly and the demand for effective information retrieval increases, text summarization has become a focal point of research in recent years. This study offers a thorough evaluation of four leading pre-trained and open-source large language models: BART, FLAN-T5, LLaMA-3-8B, and Gemma-7B, across five diverse datasets CNN/DM, Gigaword, News Summary, XSum, and BBC News. The evaluation employs widely recognized automatic metrics, including ROUGE-1, ROUGE-2, ROUGE-L, BERTScore, and METEOR, to assess the models' capabilities in generating coherent and informative summaries. The results reveal the comparative strengths and limitations of these models in processing various text types.

Spatial reasoning remains a challenge for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses. Experiments on a real-world tourism dataset show that Spatial-RAG significantly improves spatial question answering, bridging the gap between LLMs and spatial intelligence.

Long-context Multimodal Large Language Models (MLLMs) that incorporate long text-image and text-video modalities, demand substantial resources as their multimodal Key-Value (KV) caches grow with increasing input lengths, challenging inference efficiency. Existing methods for KV cache compression, in both text-only and multimodal LLMs, have neglected attention density variations across layers, thus often adopting uniform or progressive reduction strategies for layer-wise cache allocation. In this work, we propose MEDA, a dynamic layer-wise KV cache allocation method for efficient multimodal long-context inference. As its core, MEDA utilizes cross-modal attention entropy to determine the KV cache size at each MLLMs layer. Given the dynamically allocated KV cache size at each layer, MEDA also employs a KV pair selection scheme to identify which KV pairs to select and a KV pair merging strategy that merges the selected and non-selected ones to preserve information from the entire context. MEDA achieves up to 72% KV cache memory reduction and 2.82 times faster decoding speed, while maintaining or enhancing performance on various multimodal tasks in long-context settings, including multi-images and long-video scenarios. Our code is released at https://github.com/AIoT-MLSys-Lab/MEDA.

Retrieval-Augmented Large Language Models (LLMs), which integrate external knowledge into LLMs, have shown remarkable performance in various medical domains, including clinical diagnosis. However, existing RAG methods struggle to effectively assess task difficulty to make retrieval decisions, thereby failing to meet the clinical requirements for balancing efficiency and accuracy. So in this paper, we propose FIND (\textbf{F}ine-grained \textbf{In}formation \textbf{D}ensity Guided Adaptive RAG), a novel framework that improves the reliability of RAG in disease diagnosis scenarios. FIND incorporates a fine-grained adaptive control module to determine whether retrieval is necessary based on the information density of the input. By optimizing the retrieval process and implementing a knowledge filtering module, FIND ensures that the retrieval is better suited to clinical scenarios. Experiments on three Chinese electronic medical record datasets demonstrate that FIND significantly outperforms various baseline methods, highlighting its effectiveness in clinical diagnosis tasks.

Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental statistical limits concerning aligning LLMs with human preferences, with a focus on the probabilistic representation of human preferences and the preservation of diverse preferences in aligned LLMs. We first show that human preferences can be represented by a reward model if and only if the preference among LLM-generated responses is free of any Condorcet cycle. Moreover, we prove that Condorcet cycles exist with probability converging to one exponentially fast under a probabilistic preference model, thereby demonstrating the impossibility of fully aligning human preferences using reward-based approaches such as reinforcement learning from human feedback. Next, we explore the conditions under which LLMs would employ mixed strategies -- meaning they do not collapse to a single response -- when aligned in the limit using a non-reward-based approach, such as Nash learning from human feedback (NLHF). We identify a necessary and sufficient condition for mixed strategies: the absence of a response that is preferred over all others by a majority. As a blessing, we prove that this condition holds with high probability under the probabilistic preference model, thereby highlighting the statistical possibility of preserving minority preferences without explicit regularization in aligning LLMs. Finally, we leverage insights from our statistical results to design a novel, computationally efficient algorithm for finding Nash equilibria in aligning LLMs with NLHF. Our experiments show that Llama-3.2-1B, aligned with our algorithm, achieves a win rate of 60.55\% against the base model.