4157 papers
The paper introduces Decision-Aware Counterfactual Alignment (DACA), a framework that mitigates bias in LLM recommendations by penalizing cue-induced differences in final outputs while preserving legitimate personalization, thereby significantly improving recommendation fairness and academic fit without sacrificing responsiveness to relevant user attributes.
This paper proposes a blockchain-empowered framework for secure educational data sharing that integrates privacy, traceability, and accountability through novel cross-module binding protocols and formal security proofs, demonstrating minimal performance overhead while effectively mitigating interface-level attack vectors.
This paper proposes ControlNet-guided Low-Rank Adaptation (\method), a parameter-efficient, mask-conditioned latent diffusion framework that synthesizes realistic MRI images to significantly improve segmentation performance when real training data is scarce, outperforming existing methods in distributional similarity and segmentation metrics on BraTS and ACDC datasets.
This paper demonstrates that GGUF quantization levels do not exhibit monotonic performance degradation, as specific bit-widths can unexpectedly trigger high rates of format failures and non-answers that are unpredictable from their labels or neighboring precision levels, thereby distorting standard accuracy benchmarks.
This paper introduces TruthLens, an evidence-based pipeline that detects hallucinations in large language model responses by extracting individual claims, retrieving evidence via a hybrid BM25 and MiniLM approach, and verifying them with a DeBERTa-v3 NLI model, achieving moderate accuracy on the FEVER dataset while highlighting limitations in generalization and evidence coverage.
This paper proposes Recursive Lexical Combination (RLC), a corpus-driven method that efficiently constructs Chinese domain lexicons by recursively expanding lexical units to significantly reduce candidate search space while retaining high recall of emerging terminology, as demonstrated through validation on national-level data asset policy texts.
While frontier language models successfully recover established scientific quality hierarchies and achieve higher inter-model agreement than human reviewers, they systematically underweight originality and exhibit weak alignment with humans in identifying paper weaknesses, revealing structural asymmetries in the review process.
The paper proposes CGMU-Net, a classification-guided cross-interaction network that integrates attention fusion, channel-wise enhancement, and lesion-aware modules to achieve accurate and robust dermoscopic skin lesion segmentation by addressing challenges like irregular shapes and blurred boundaries.
This paper demonstrates that fine-tuning transformer-based models, specifically XLM-RoBERTa, with generative data augmentation significantly improves Named Entity Recognition performance and generalization for low-resource pre-modern Serbian Cyrillic texts, achieving an in-domain F1-score of approximately 0.92 and establishing a recommended model trained with 50% synthetic data for broader historical research.
Based on a survey of 384 professionals in China's integrated circuit manufacturing sector, this study finds that organizational deep learning application capability enhances manufacturing quality performance by sequentially improving quality inspection effectiveness and quality risk identification capability.