AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles are written and how they are applied. But while legal systems use institutional safeguards to manage such ambiguity, such as transparent appellate review policing interpretive constraints, AI alignment pipelines offer no comparable protections. Different interpretations of the same rule can lead to inconsistent or unstable model behavior. Drawing on legal theory, we identify key gaps in current alignment pipelines by examining how legal systems constrain ambiguity at both the rule creation and rule application steps. We then propose a computational framework that mirrors two legal mechanisms: (1) a rule refinement pipeline that minimizes interpretive disagreement by revising ambiguous rules (analogous to agency rulemaking or iterative legislative action), and (2) prompt-based interpretive constraints that reduce inconsistency in rule application (analogous to legal canons that guide judicial discretion). We evaluate our framework on a 5,000-scenario subset of the WildChat dataset and show that both interventions significantly improve judgment consistency across a panel of reasonable interpreters. Our approach offers a first step toward systematically managing interpretive ambiguity, an essential step for building more robust, law-following AI systems.

Recent advances in multimodal large language models (MLLMs) have led to much progress in video understanding tasks. To avoid the heavy computational cost of processing all frames, these models typically rely on keyframe sampling methods guided by vision-language encoders (\textit{e.g.,} SigLIP). However, it remains unclear whether such encoders can truly identify the most informative frames. In this work, we provide several empirical pieces of evidence revealing that popular vision encoders critically suffer from their limited capability to identify where the MLLM should look inside the video to handle the given textual query appropriately. Our findings suggest that the development of better keyframe identification techniques may be necessary for efficient video MLLMs.

Cross-lingual Named Entity Recognition (CL-NER) aims to transfer knowledge from high-resource languages to low-resource languages. However, existing zero-shot CL-NER (ZCL-NER) approaches primarily focus on Latin script language (LSL), where shared linguistic features facilitate effective knowledge transfer. In contrast, for non-Latin script language (NSL), such as Chinese and Japanese, performance often degrades due to deep structural differences. To address these challenges, we propose an entity-aligned translation (EAT) approach. Leveraging large language models (LLMs), EAT employs a dual-translation strategy to align entities between NSL and English. In addition, we fine-tune LLMs using multilingual Wikipedia data to enhance the entity alignment from source to target languages.

We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right, Dream-Coder 7B adaptively determines its decoding strategy based on the coding task: sketch-first generation for complex algorithms, left-to-right generation for straightforward completions, and interleaved reasoning generation for code understanding tasks. We adapt a pretrained AR checkpoint to a discrete diffusion frameworks with a continuous-time weighted cross-entropy objective. Our post-training recipe comprises (i) supervised fine-tuning, where we mitigate padding pathologies via random truncation and a padding penalty to improve sample efficiency and stabilize generation; and (ii) reinforcement learning with verifiable rewards over a curated high-quality prompt set drawn from open-source datasets, using a tailored reinforcement learning recipe for diffusion language models. The resulting Dream-Coder 7B Instruct attains 21.4\% pass@1 on LiveCodeBench (2410--2505) and demonstrates competitive performance on HumanEval, MBPP, BigCodeBench, and CRUXEval. We release Dream-Coder-7B and Dream-Coder-7B-Instruct checkpoints, training recipes, preprocessing pipelines, and inference code to facilitate reproducibility and further research.

How does the natural evolution of context paragraphs affect question answering in generative Large Language Models (LLMs)? To investigate this, we propose a framework for curating naturally evolved, human-edited variants of reading passages from contemporary QA benchmarks and for analyzing LLM performance across a range of semantic similarity scores, which quantify how closely each variant aligns with content seen during pretraining. Using this framework, we evaluate six QA datasets and eight LLMs with publicly available training data. Our experiments reveal that LLM performance declines as reading passages naturally diverge from the versions encountered during pretraining-even when the question and all necessary information remains present at inference time. For instance, average model accuracy on BoolQ drops by over 30% from the highest to lowest similarity bins, with slopes exceeding 70 across several LLMs. These findings suggest that natural text evolution poses a significant challenge to the language understanding capabilities of LLMs.

Large language models (LLMs) struggle to navigate culturally specific communication norms, limiting their effectiveness in global contexts. We focus on Persian taarof, a social norm in Iranian interactions, which is a sophisticated system of ritual politeness that emphasizes deference, modesty, and indirectness, yet remains absent from existing cultural benchmarks. We introduce TaarofBench, the first benchmark for evaluating LLM understanding of taarof, comprising 450 role-play scenarios covering 12 common social interaction topics, validated by native speakers. Our evaluation of five frontier LLMs reveals substantial gaps in cultural competence, with accuracy rates 40-48% below native speakers when taarof is culturally appropriate. Performance varies between interaction topics, improves with Persian-language prompts, and exhibits gender-based asymmetries. We also show that responses rated "polite" by standard metrics often violate taarof norms, indicating the limitations of Western politeness frameworks. Through supervised fine-tuning and Direct Preference Optimization, we achieve 21.8% and 42.3% improvement in model alignment with cultural expectations. Our human study with 33 participants (11 native Persian, 11 heritage, and 11 non-Iranian speakers) forms baselines in varying degrees of familiarity with Persian norms. This work lays the foundation for developing diverse and culturally aware LLMs, enabling applications that better navigate complex social interactions.

Inductive reasoning enables humans to infer abstract rules from limited examples and apply them to novel situations. In this work, we compare an LLM-based hypothesis search framework with direct program generation approaches on few-shot rule induction tasks. Our findings show that hypothesis search achieves performance comparable to humans, while direct program generation falls notably behind. An error analysis reveals key bottlenecks in hypothesis generation and suggests directions for advancing program induction methods. Overall, this paper underscores the potential of LLM-based hypothesis search for modeling inductive reasoning and the challenges in building more efficient systems.

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning and generation tasks. However, their proficiency in complex causal reasoning, discovery, and estimation remains an area of active development, often hindered by issues like hallucination, reliance on spurious correlations, and difficulties in handling nuanced, domain - specific, or personalized causal relationships. Multi - agent system s, leveraging the collaborative or specialized abilities of multiple LLM - based agents, are emerging as a powerful paradigm to address these limitations. This review paper explores the burgeoning field of causal multi - agent LLMs. We examine how these system s are designed to tackle different facets of causality, including causal reasoning and counterfactual analysis, causal discovery from data, and the estimation of causal effects. We delve into the diverse architectural patterns and interaction protocols emp loyed, from pipeline - based processing and debate frameworks to simulation environments and iterative refinement loops. Furthermore, we discuss the evaluation methodologies, benchmarks, and diverse application domains where causal multi - agent LLMs are makin g an impact, including scientific discovery, healthcare, fact - checking, and personalized systems. Finally, we highlight the persistent challenges, open research questions, and promising future directions in this synergistic field, aiming to provide a compr ehensive overview of its current state and potential trajectory. 1. Introduction

Large Language Models (LLMs) are increasingly deployed in mission-critical systems, facilitating tasks such as satellite operations, command-and-control, military decision support, and cyber defense. Many of these systems are accessed through application programming interfaces (APIs). When such APIs lack robust access controls, they can expose full or top-k logits, creating a significant and often overlooked attack surface. Prior art has mainly focused on reconstructing the output projection layer or distilling surface-level behaviors. However, regenerating a black-box model under tight query constraints remains underexplored. We address that gap by introducing a constrained replication pipeline that transforms partial logit leakage into a functional deployable substitute model clone. Our two-stage approach (i) reconstructs the output projection matrix by collecting top-k logits from under 10k black-box queries via singular value decomposition (SVD) over the logits, then (ii) distills the remaining architecture into compact student models with varying transformer depths, trained on an open source dataset. A 6-layer student recreates 97.6% of the 6-layer teacher model's hidden-state geometry, with only a 7.31% perplexity increase, and a 7.58 Negative Log-Likelihood (NLL). A 4-layer variant achieves 17.1% faster inference and 18.1% parameter reduction with comparable performance. The entire attack completes in under 24 graphics processing unit (GPU) hours and avoids triggering API rate-limit defenses. These results demonstrate how quickly a cost-limited adversary can clone an LLM, underscoring the urgent need for hardened inference APIs and secure on-premise defense deployments.

Large Language Models (LLMs) are increasingly used for accessibility guidance, yet many disability groups remain underserved by their advice. To address this gap, we present taxonomy aligned benchmark1 of human validated, general purpose accessibility questions, designed to systematically audit inclusivity across disabilities. Our benchmark evaluates models along three dimensions: Question-Level Coverage (breadth within answers), Disability-Level Coverage (balance across nine disability categories), and Depth (specificity of support). Applying this framework to 17 proprietary and open-weight models reveals persistent inclusivity gaps: Vision, Hearing, and Mobility are frequently addressed, while Speech, Genetic/Developmental, Sensory-Cognitive, and Mental Health remain under served. Depth is similarly concentrated in a few categories but sparse elsewhere. These findings reveal who gets left behind in current LLM accessibility guidance and highlight actionable levers: taxonomy-aware prompting/training and evaluations that jointly audit breadth, balance, and depth.