Large-scale empirical analysis of authentic student-GenAI interactions reveals concentrated recurring patterns that vary by course and form of academic work.
29.Carion, N.et al.Sam 3: Segment anything with concepts (2025)
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
dataset 1
method 1
citation-polarity summary
representative citing papers
Retrieval-augmented LLMs produce more cautious and guideline-aligned recommendations on cannabidiol for older adults than standalone models, demonstrated via automated evaluation on 64 diverse scenarios.
Releases the first large-scale expert-annotated corpus of Chinese central government policy directives (1949-2023) labeled with a five-color clear/ambiguous taxonomy and high inter-annotator reliability.
Generative AI enables scalable, context-aware spear phishing by extracting profiles from public social media, producing emails that outperform real-world phishing samples in personalization and lower recipient suspicion.
LLM agents can reconstruct high-fidelity personal profiles from minimal PII seeds with over 90% accuracy in under 10 minutes at less than $3 cost, exposing three escalating tiers of privacy risks.
GMRL-BD detects untrustworthy topic boundaries for black-box LLMs by combining bias-diffusion on a Wikipedia KG with multi-agent RL, supported by a released dataset labeling biases in models like Llama2 and Qwen2.
A new leaf-instance dataset for soybean-cotton detection and segmentation collected across growth stages and conditions from commercial farms is presented and validated with YOLOv11.
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
A cognitive-uncertainty guided two-stage KD framework filters to 10.3% of samples to reach 0.9585 MAP@3 and 84.38% accuracy with a 4B model, beating larger LLMs on misconception classification.
An LLM-as-a-judge evaluation framework for math reasoning outperforms symbolic methods by accurately assessing diverse answer representations and formats.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
citing papers explorer
No citing papers match the current filters.