Despite ASR technology being full-scale adopted by industry and for large portions of the population, ASR systems often have errors that require editors to post-edit text quality. While LLMs are powerful post-editing tools, baseline full rewrite models have inference inefficiencies because they often generate the same redundant text over and over again. Compact edit representations have existed but often lack the efficacy and context required for optimal accuracy. This paper introduces CEGER (Context-Enhanced Granular Edit Representation), a compact edit representation that was generated for highly accurate, efficient ASR post-editing. CEGER allows LLMs to generate a sequence of structured, fine-grained, contextually rich commands to modify the original ASR output. A separate expansion module deterministically reconstructs the corrected text based on the commands. Extensive experiments on the LibriSpeech dataset that were conducted, CEGER achieves state-of-the-art accuracy, achieving the lowest word error rate (WER) versus full rewrite and prior compact representations.

High temporal resolution is essential for capturing fine-grained details in video understanding. However, current video large language models (VLLMs) and benchmarks mostly rely on low-frame-rate sampling, such as uniform sampling or keyframe selection, discarding dense temporal information. This compromise avoids the high cost of tokenizing every frame, which otherwise leads to redundant computation and linear token growth as video length increases. While this trade-off works for slowly changing content, it fails for tasks like lecture comprehension, where information appears in nearly every frame and requires precise temporal alignment. To address this gap, we introduce Dense Video Understanding (DVU), which enables high-FPS video comprehension by reducing both tokenization time and token overhead. Existing benchmarks are also limited, as their QA pairs focus on coarse content changes. We therefore propose DIVE (Dense Information Video Evaluation), the first benchmark designed for dense temporal reasoning. To make DVU practical, we present Gated Residual Tokenization (GRT), a two-stage framework: (1) Motion-Compensated Inter-Gated Tokenization uses pixel-level motion estimation to skip static regions during tokenization, achieving sub-linear growth in token count and compute. (2) Semantic-Scene Intra-Tokenization Merging fuses tokens across static regions within a scene, further reducing redundancy while preserving dynamic semantics. Experiments on DIVE show that GRT outperforms larger VLLM baselines and scales positively with FPS. These results highlight the importance of dense temporal information and demonstrate that GRT enables efficient, scalable high-FPS video understanding.

Recent advancements in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI). Among the essential capabilities required for AGI, creativity has emerged as a critical trait for MLLMs, with association serving as its foundation. Association reflects a model' s ability to think creatively, making it vital to evaluate and understand. While several frameworks have been proposed to assess associative ability, they often overlook the inherent ambiguity in association tasks, which arises from the divergent nature of associations and undermines the reliability of evaluations. To address this issue, we decompose ambiguity into two types-internal ambiguity and external ambiguity-and introduce AssoCiAm, a benchmark designed to evaluate associative ability while circumventing the ambiguity through a hybrid computational method. We then conduct extensive experiments on MLLMs, revealing a strong positive correlation between cognition and association. Additionally, we observe that the presence of ambiguity in the evaluation process causes MLLMs' behavior to become more random-like. Finally, we validate the effectiveness of our method in ensuring more accurate and reliable evaluations. See Project Page for the data and codes.

This paper discusses our exploration of different data-efficient and parameter-efficient approaches to Arabic Dialect Identification (ADI). In particular, we investigate various soft-prompting strategies, including prefix-tuning, prompt-tuning, P-tuning, and P-tuning V2, as well as LoRA reparameterizations. For the data-efficient strategy, we analyze hard prompting with zero-shot and few-shot inferences to analyze the dialect identification capabilities of Large Language Models (LLMs). For the parameter-efficient PEFT approaches, we conducted our experiments using Arabic-specific encoder models on several major datasets. We also analyzed the n-shot inferences on open-source decoder-only models, a general multilingual model (Phi-3.5), and an Arabic-specific one(SILMA). We observed that the LLMs generally struggle to differentiate the dialectal nuances in the few-shot or zero-shot setups. The soft-prompted encoder variants perform better, while the LoRA-based fine-tuned models perform best, even surpassing full fine-tuning.

Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have become increasingly longer, which incurs higher computational costs. To address this prompt inflation problem, prompt compression has been proposed. However, most existing methods require training a small auxiliary model for compression, incurring a significant amount of additional computation. To avoid this, we propose a two-stage, training-free approach, called Dual-Stage Progressive Compression (DSPC). In the coarse-grained stage, semantic-related sentence filtering removes sentences with low semantic value based on TF-IDF. In the fine-grained stage, token importance is assessed using attention contribution, cross-model loss difference, and positional importance, enabling the pruning of low-utility tokens while preserving semantics. We validate DSPC on LLaMA-3.1-8B-Instruct and GPT-3.5-Turbo under a constrained token budget and observe consistent improvements. For instance, in the FewShot task of the Longbench dataset, DSPC achieves a performance of 49.17 by using only 3x fewer tokens, outperforming the best state-of-the-art baseline LongLLMLingua by 7.76.

Social scientists are now using large language models to create " silicon samples" - synthetic datasets intended to stand in for human respondents, aimed at revolutionising human subjects research. However, there are many analytic choices which must be made to produce these samples. Though many of these choices are defen sible, their impact on sample quality is poorly understood . I map out these analytic choices and demonstrate how a very small number of decisions can dramatically change the correspondence between silicon samples and human data. Configurations (N = 252) varied substantially in their capacity to estimate (i) rank ordering of participants, (ii) response distributions, and (iii) between - scale correlations. Most critically, configurations were not consistent in quality: those that performed well on one dimension often performed poorly on another, implying that there i s no "one - size - fits - all" configuration that optimises the accuracy of these samples. I call for greater attention to the threat of analytic flexibility in using silicon samples. Generative large language models (LLMs) have ushered in a sea change within the social sciences. The capacity of these models to produce sensical natural language output to queries, as well as their flexibility, efficiency, and generalisability, has led re searchers to explore their use in tasks across the research process. One of the most ambitious proposed uses of LLMs in this respect has been to use them as simulated research participants to determine how human participants might respond to a particular context, set of survey questions, or intervention (Cui et al., 2025). This is based on the tacit assumption that, on some level, the corpuses of data which LLMs are trained on may enable them to approximate similar data - generating processes to those which underpin human responses (Z. If achievable, this could have a transformative impact on the social sciences.

ABSTRACT With the rapid progress of large audio-language models (LALMs), audio question answering (AQA) has emerged as a challenging task requiring both fine-grained audio understanding and complex reasoning. While current methods mainly rely on constructing new datasets via captioning or reasoning traces, existing high-quality AQA data remains underutilized. To address this, we propose Omni-CLST, an error-aware Curriculum Learning framework with guided Selective Chain-of-Thought. The framework efficiently leverages existing high-quality dataset through two key strategies: an error-aware curriculum that organizes samples by difficulty, and a guided thought dropout mechanism that focuses reasoning on challenging cases. Experiments show that Omni-CLST achieves 73.80% on MMAU-mini and a new state of the art of 64.30% on MMAR, demonstrating robust generalization in multimodal audio-language understanding.

As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, EthosAgents, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.

Psychological measurement is critical to many disciplines. Despite advances in measurement, building nomological networks, theoretical maps of how concepts and measures relate to establish validity, remains a challenge 70 years after Cronbach and Meehl proposed them as fundamental to validation. This limitation has practical consequences: clinical trials may fail to detect treatment effects, and public policy may target the wrong outcomes. We introduce Analysis of Latent Indicators to Generate Nomological Structures (ALIGNS), a large language model-based system trained with validated questionnaire measures. ALIGNS provides three comprehensive nomological networks containing over 550,000 indicators across psychology, medicine, social policy, and other fields. This represents the first application of large language models to solve a foundational problem in measurement validation. We report classification accuracy tests used to develop the model, as well as three evaluations. In the first evaluation, the widely used NIH PROMIS anxiety and depression instruments are shown to converge into a single dimension of emotional distress. The second evaluation examines child temperament measures and identifies four potential dimensions not captured by current frameworks, and questions one existing dimension. The third evaluation, an applicability check, engages expert psychometricians who assess the system's importance, accessibility, and suitability. ALIGNS is freely available at nomologicalnetwork.org, complementing traditional validation methods with large-scale nomological analysis.

ABSTRACT Agricultural robotic agents have been becoming powerful helpers in a wide range of agricultural tasks, however, still heavily rely on manual operation or fixed railways for movement. To address this limitation, the AgriVLN method and the A2A benchmark pioneeringly extend Vision-and-Language Navigation (VLN) to the agricultural domain, enabling agents to navigate to the target positions following the natural language instructions. AgriVLN effectively understands the simple instructions, but often misunderstands the complex ones. To bridge this gap, we propose the method of Translator for Agricultural Robotic Agents on Vision-and-Language Navigation (T -araVLN), in which the Instruction Translator module translates the original instruction to be more refined and precise. When evaluated on the A2A benchmark, our T - araVLN effectively improves Success Rate from 0.47 to 0.63 and reduces Navigation Error from 2.91m to 2.28m, demonstrating the state-of-the-art performance in the agricultural domain.