会员服务
AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course
Arxiv
0+阅读 · 2月18日
Empathetic Cascading Networks: A Multi-Stage Prompting Technique for Reducing Social Biases in Large Language Models
Arxiv
0+阅读 · 2月19日
Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores
Arxiv
0+阅读 · 2月18日
Statistical Inference Leveraging Synthetic Data with Distribution-Free Guarantees
Arxiv
0+阅读 · 2月18日
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution
Arxiv
0+阅读 · 2月18日
SCAR: Satellite Imagery-Based Calibration for Aerial Recordings
Arxiv
0+阅读 · 2月18日
In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
Arxiv
0+阅读 · 2月17日
A Differential Fuzzing-Based Evaluation of Functional Equivalence in LLM-Generated Code Refactorings
Arxiv
0+阅读 · 2月17日
Unforgeable Watermarks for Language Models via Robust Signatures
Arxiv
0+阅读 · 2月17日
Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
Arxiv
0+阅读 · 2月17日
Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization
Arxiv
0+阅读 · 2月17日
More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles
Arxiv
0+阅读 · 2月12日
CCiV: A Benchmark for Structure, Rhythm and Quality in LLM-Generated Chinese \textit{Ci} Poetry
Arxiv
0+阅读 · 2月15日
Designing Staged Evaluation Workflows for LLMs: Integrating Domain Experts, Lay Users, and Model-Generated Evaluation Criteria
Arxiv
0+阅读 · 2月16日
AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
Arxiv
0+阅读 · 2月13日
参考链接
微信扫码咨询专知VIP会员
Top