1071 papers
This paper demonstrates that addressing the ecological fallacy by modeling an author's language context through a specific task called HuLM, particularly during fine-tuning (HuFT) or continued pre-training, significantly improves the performance of an 8B Llama model across multiple downstream tasks compared to standard training methods.
This paper proposes a Structured Style-Rewrite Framework that combines explicit disentanglement of stylistic dimensions with implicit Chain-of-Thought conditioning to enable small language models to achieve high-fidelity, consistent character role-playing without requiring explicit reasoning tokens during inference.
This paper proposes an interpretable modeling approach that integrates person-level psychological traits with situational context features derived from social media data to predict dynamic mental well-being, demonstrating that theory-driven methods offer competitive performance and greater human-understandable insights compared to standard language model embeddings.
The paper introduces ProCap, a novel framework that improves change captioning by reformulating static image comparison into dynamic procedure modeling through a two-stage design that learns latent change dynamics from sparse keyframes and utilizes learnable procedure queries to generate temporally coherent descriptions of how changes occur.
Track-SQL is a novel framework that enhances generative language models for multi-turn Text-to-SQL tasks by integrating dual-extractive modules for semantic schema and context tracking, achieving state-of-the-art performance on the SparC and CoSQL datasets.
This paper introduces MASFactory, a graph-centric framework that utilizes a human-in-the-loop "Vibe Graphing" approach to automatically compile natural language intents into executable multi-agent system workflows, thereby addressing challenges in manual implementation, component reuse, and context integration while demonstrating effectiveness across seven public benchmarks.
ViewFusion is a two-stage framework that enhances multi-view spatial reasoning in vision-language models by explicitly separating cross-view spatial pre-alignment from question-driven reasoning, achieving significant accuracy improvements on benchmarks like MMSI-Bench through synthetic supervision and reinforcement learning.
This paper evaluates the performance of four state-of-the-art open-weight Large Language Models on Austrian A-level German essay grading using rubric-based prompts, finding that while they can apply standardized criteria, their low agreement rates with human experts (maximum 40.6% on sub-dimensions and 32.8% on final grades) render them currently unsuitable for real-world automated scoring.
This study demonstrates that exposing Large Language Models to domain-specific texts via continued pre-training shapes distinct machine personalities that influence problem-solving, revealing a "Suppression Advantage" where reduced social traits enhance complex reasoning while identifying a bimodal competence peak between "Expressive Generalists" and "Suppressed Specialists."
DeepSight is the first dedicated depth-driven multimodal large language model that leverages single-channel depth maps, a novel depth instruction dataset, and a modified ViT encoder to significantly enhance 3D scene understanding and spatial reasoning capabilities.
This paper proposes a neuro-symbolic pipeline that integrates large language models for generating implicit premises and translating natural language into logical formulas, alongside a SAT-based reasoner, to systematically decode enthymemes and verify logical entailment, demonstrating promising performance on existing datasets.
This paper proposes a zero-shot mechanism that leverages latent prompt representations to dynamically crop the fixed context window of Diffusion Language Models before generation, significantly reducing computational costs while maintaining or improving performance across diverse tasks.
This paper proposes a graph-based framework that models narratives as entity-interaction graphs and employs causal estimation to distill minimal causal subgraphs, thereby achieving superior performance in classifying oppositional narratives while mitigating the biases inherent in traditional black-box models.
This paper introduces RAPTOR, a controlled study demonstrating that multilingual HuBERT pre-training, rather than model scale, is the primary driver of cross-domain robustness and reliable calibration in compact audio deepfake detection systems.
This paper proposes a two-stage framework that first trains a contrastive encoder on labeled invented alphabets and then uses teacher-student distillation to learn unsupervised, deformation-invariant embeddings for historically attested scripts, effectively bridging supervised discriminative learning with unsupervised discovery of latent cross-script similarities without requiring ground-truth evolutionary relationships.
This paper introduces CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that leverages patient context, guideline-based severity weighting, and a comprehensive error taxonomy to achieve superior alignment with radiologist judgments compared to existing metrics.
The paper proposes MAPO, a critic-free reinforcement learning algorithm that combines dense process feedback from a judge model with a mixed advantage estimator to enable stable, scalable, and high-performing long-horizon multi-turn dialogue optimization in subjective tasks like emotional support.
This paper introduces the AI-CROWD protocol, which approximates ground truth for large-scale content analysis by aggregating the consensus outputs of an ensemble of large language models to overcome the cost and consistency limitations of human coding.
This paper introduces LIT-RAGBench, a comprehensive benchmark dataset and evaluation framework designed to systematically assess Large Language Models' capabilities in Retrieval-Augmented Generation across five critical categories—Integration, Reasoning, Logic, Table, and Abstention—using a mix of human-constructed Japanese questions and curated English translations to guide model selection and development for practical RAG deployments.
FlashPrefill is a novel framework that achieves ultra-fast long-context prefilling by combining instantaneous block-searching for dynamic sparse patterns with a thresholding mechanism to eliminate long-tail attention scores, delivering up to a 27.78x speedup on 256K sequences while maintaining efficiency on shorter contexts.