AI & Sentiment Analysis
![[2410.13098] A Little Human Data Goes A Long Way](https://i1.wp.com/arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png?ssl=1 "[2410.13098] A Little Human Data Goes A Long Way"){kind=logo}
[2410.13098] A Little Human Data Goes A Long Way
View a PDF of the paper titled A Little Human Data Goes A Long Way, by Dhananjay Ashok and Jonathan...
Read moreDetailsA Comprehensive Assessment of Open-Source Large Language Models
View a PDF of the paper titled Hallucinations and Key Information Extraction in Medical Texts: A Comprehensive Assessment of Open-Source...
Read moreDetailsHarnessing Frontier Models to Structure Real-World Data at Scale
Authors:Cliff Wong, Sam Preston, Qianchu Liu, Zelalem Gero, Jaspreet Bagga, Sheng Zhang, Shrey Jain, Theodore Zhao, Yu Gu, Yanbo Xu,...
Read moreDetails[2411.02083] Regress, Don’t Guess — A Regression-like Loss on Number Tokens for Language Models
Authors:Jonas Zausinger, Lars Pennig, Anamarija Kozina, Sean Sdahl, Julian Sikora, Adrian Dendorfer, Timofey Kuznetsov, Mohamad Hagog, Nina Wiedemann, Kacper Chlodny,...
Read moreDetailsGeneralize across Homophily and Heterophily: Hybrid Spectral Graph Pre-Training and Prompt Tuning
arXiv:2508.11328v1 Announce Type: cross Abstract: Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer...
Read moreDetailsORFuzz: Fuzzing the "Other Side" of LLM Safety — Testing Over-Refusal
arXiv:2508.11222v1 Announce Type: cross Abstract: Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly...
Read moreDetailsOptimizing Rotation Transformation for Quantization for Free
View a PDF of the paper titled Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free, by Euntae Choi...
Read moreDetailsUnlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs
View a PDF of the paper titled ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs, by Keyu...
Read moreDetailsAI Blob! LLM-Driven Recontextualization of Italian Television Archives
arXiv:2508.09535v1 Announce Type: cross Abstract: This paper introduces AI Blob!, an experimental system designed to explore the potential of semantic...
Read moreDetails[2508.06671] Do Biased Models Have Biased Thoughts?
View a PDF of the paper titled Do Biased Models Have Biased Thoughts?, by Swati Rajwal and 3 other authors...
Read moreDetails
Recent News
We bring you the best Premium WordPress Themes that perfect for news, magazine, personal blog, etc. Check our landing page for details.