Knowledge catalogue
arXiv:2604.17293v1 Announce Type: new Abstract: Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic 'I don't k
arXiv:2604.18169v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for creative tasks such as literary translation. Yet translational creativity remains underexplored a
arXiv:2602.07954v4 Announce Type: replace Abstract: As Large Language Models (LLMs) become increasingly deployed in Polish language applications, the need for efficient and accurate content safety cla
arXiv:2510.08986v2 Announce Type: replace Abstract: We introduce CAPC-CG, the Chinese Adaptive Policy Communication (Central Government) Corpus, the first open dataset of Chinese policy directives ann
arXiv:2604.17501v1 Announce Type: new Abstract: Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated p
arXiv:2601.06394v3 Announce Type: replace Abstract: Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predic
arXiv:2604.18005v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the
arXiv:2604.17210v1 Announce Type: new Abstract: Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing sa
arXiv:2604.17010v1 Announce Type: new Abstract: We introduce a self-play framework for semantic equivalence in Haskell, utilizing formal verification to guide adversarial training between a generator
arXiv:2604.18419v1 Announce Type: cross Abstract: Large language models (LLMs) using chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can m
arXiv:2604.04815v2 Announce Type: replace Abstract: The rapid development of Large Language Models (LLMs) has transformed fake news detection and fact-checking tasks from simple classification to comp
arXiv:2507.02850v3 Announce Type: replace Abstract: We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behav
arXiv:2601.18731v2 Announce Type: replace Abstract: Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individu
arXiv:2604.16957v1 Announce Type: new Abstract: We present Open-TQ-Metal, the first implementation of fused compressed-domain attention on Apple Silicon, enabling 128K-context inference for Llama 3.1
arXiv:2604.16909v1 Announce Type: new Abstract: As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in h
arXiv:2406.08334v2 Announce Type: replace-cross Abstract: Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constra
arXiv:2601.02970v2 Announce Type: replace Abstract: Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency m
arXiv:2604.16453v1 Announce Type: new Abstract: We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding m
arXiv:2604.17433v1 Announce Type: new Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but
arXiv:2405.13068v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Cu
arXiv:2604.17031v1 Announce Type: new Abstract: The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds. We approach this pr
arXiv:2508.06094v4 Announce Type: replace Abstract: Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhi
arXiv:2510.07774v3 Announce Type: replace Abstract: In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning abil
arXiv:2604.16115v1 Announce Type: new Abstract: Hyperspectral tree species classification is challenging due to limited and imbalanced class labels, spectral mixing (overlapping light signatures from
arXiv:2604.15873v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. In this line of work, models are commonly evaluated both
arXiv:2604.16058v1 Announce Type: cross Abstract: The rapid proliferation of Large Language Models (LLMs) in software development has made distinguishing AI-generated code from human-written code a cr
arXiv:2509.19104v2 Announce Type: replace Abstract: Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing
arXiv:2604.15859v1 Announce Type: cross Abstract: Forecasting has become a natural benchmark for reasoning under uncertainty. Yet existing evaluations of large language models remain limited to judgme
arXiv:2510.22977v2 Announce Type: replace-cross Abstract: Enhancing the reasoning capabilities of Large Language Models (LLMs) is a key strategy for building Agents that 'think then act.' However, rec
arXiv:2604.15306v1 Announce Type: cross Abstract: Whether language models can systematically generalize remains actively debated. Yet empirical performance is jointly shaped by multiple factors such a
arXiv:2604.02585v2 Announce Type: replace-cross Abstract: LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious contextual information can introduce harmful bia
arXiv:2604.14198v1 Announce Type: cross Abstract: Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains large
arXiv:2604.14631v1 Announce Type: new Abstract: Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing app
arXiv:2604.13114v1 Announce Type: cross Abstract: Code smells and software vulnerabilities both increase maintenance cost, yet they are often handled by separate tools that miss structural context and
arXiv:2507.15066v5 Announce Type: replace Abstract: Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanat
arXiv:2604.13061v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in high-stakes autonomous and interactive workflows, where reliability demands continuous, multi-
arXiv:2601.15550v3 Announce Type: replace Abstract: Existing cultural commonsense benchmarks treat nations as monolithic, assuming uniform practices within national boundaries. But does cultural commo
arXiv:2604.13071v1 Announce Type: new Abstract: We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Int
arXiv:2604.13556v1 Announce Type: new Abstract: Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the m
arXiv:2604.12469v1 Announce Type: new Abstract: Fine-tuning is the dominant paradigm for adapting pretrained large language models (LLMs) to downstream NLP tasks. In practice, fine-tuning datasets may
arXiv:2604.12191v1 Announce Type: new Abstract: Current evaluations of large language models aggregate performance across diverse tasks into single scores. This obscures fine-grained ability variation
arXiv:2603.24647v4 Announce Type: replace Abstract: The autoresearch repository enables an LLM agent to optimize hyperparameters by editing training code directly. We use it as a testbed to compare cl
arXiv:2604.12843v1 Announce Type: new Abstract: The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are
arXiv:2604.12806v1 Announce Type: new Abstract: Inferring latent interaction structures from observed dynamics is a fundamental inverse problem in many-body interacting systems. Most neural approaches
arXiv:2604.12627v1 Announce Type: new Abstract: RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based R
arXiv:2604.12108v1 Announce Type: cross Abstract: Integration testing is critical for the quality and reliability of complex software systems. However, diagnosing their failures presents significant c
arXiv:2604.12373v1 Announce Type: new Abstract: Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether larg
arXiv:2508.04559v3 Announce Type: replace Abstract: Recent diffusion-based approaches have made significant advances in image-based virtual try-on, enabling more realistic and end-to-end garment synth
arXiv:2604.12378v1 Announce Type: new Abstract: Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in their produ
arXiv:2603.01045v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agen
arXiv:2604.11840v1 Announce Type: new Abstract: Large language models are increasingly used as agents in social, economic, and policy simulations. A common assumption is that stronger reasoning should
arXiv:2601.16399v5 Announce Type: replace Abstract: We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optim
arXiv:2604.11119v1 Announce Type: cross Abstract: This paper reorganizes the current manuscript around the DPO versus DDO-RM preference-optimization project and focuses on two parts: the algorithmic v
arXiv:2604.11462v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle with long-horizon tasks due to the 'context bottleneck' and the 'lost-in-the-middle' phenomenon, where accumulated
arXiv:2604.11721v1 Announce Type: cross Abstract: Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. Wh
arXiv:2604.11209v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success across a wide range of applications especially when augmented by external knowledge thro
arXiv:2604.09907v1 Announce Type: cross Abstract: To improve crop genetics, high-throughput, effective and comprehensive phenotyping is a critical prerequisite. While such tasks were traditionally per
arXiv:2604.10917v1 Announce Type: new Abstract: Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficie
arXiv:2503.23514v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can carry out human-like dialogue, but unlike humans, they are stateless due to the superposition property. Howev
arXiv:2604.11446v1 Announce Type: cross Abstract: Recently, scaling reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs) has emerged as an effective training paradigm