Show newer
arXiv - CSCL

Large Language Models Are Not Strong Abstract Reasoners. (arXiv:2305.19555v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.19555

0
arXiv - CSCL

In the Name of Fairness: Assessing the Bias in Clinical Record De-identification. (arXiv:2305.11348v2 [cs.LG] UPDATED) 

arxiv.org/abs/2305.11348

0
arXiv - CSCL

Theoretical guarantees on the best-of-n alignment policy. (arXiv:2401.01879v1 [cs.LG]) 

arxiv.org/abs/2401.01879

0
arXiv - CSCL

A Vision Check-up for Language Models. (arXiv:2401.01862v1 [cs.CV]) 

arxiv.org/abs/2401.01862

0
arXiv - CSCL

Multilingual Instruction Tuning With Just a Pinch of Multilinguality. (arXiv:2401.01854v1 [cs.CL]) 

arxiv.org/abs/2401.01854

0
arXiv - CSCL

Investigating Semi-Supervised Learning Algorithms in Text Datasets. (arXiv:2401.01843v1 [cs.CL]) 

arxiv.org/abs/2401.01843

0
arXiv - CSCL

Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling. (arXiv:2401.01830v1 [cs.CL]) 

arxiv.org/abs/2401.01830

0
arXiv - CSCL

Physio: An LLM-Based Physiotherapy Advisor. (arXiv:2401.01825v1 [cs.CL]) 

arxiv.org/abs/2401.01825

0
arXiv - CSCL

Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering. (arXiv:2401.01780v1 [cs.CL]) 

arxiv.org/abs/2401.01780

0
arXiv - CSCL

Cross-target Stance Detection by Exploiting Target Analytical Perspectives. (arXiv:2401.01761v1 [cs.CL]) 

arxiv.org/abs/2401.01761

0
arXiv - CSCL

VGA: Vision and Graph Fused Attention Network for Rumor Detection. (arXiv:2401.01759v1 [cs.SI]) 

arxiv.org/abs/2401.01759

0
arXiv - CSCL

Evaluating Large Language Models in Semantic Parsing for Conversational Question Answering over Knowledge Graphs. (arXiv:2401.01711v1 [cs.CL]) 

arxiv.org/abs/2401.01711

0
arXiv - CSCL

WordArt Designer API: User-Driven Artistic Typography Synthesis with Large Language Models on ModelScope. (arXiv:2401.01699v1 [cs.CV]) 

arxiv.org/abs/2401.01699

0
arXiv - CSCL

Patterns of Persistence and Diffusibility across World's Languages. (arXiv:2401.01698v1 [cs.CL]) 

arxiv.org/abs/2401.01698

0
arXiv - CSCL

Predicting challenge moments from students' discourse: A comparison of GPT-4 to two traditional natural language processing approaches. (arXiv:2401.01692v1 [cs.CL]) 

arxiv.org/abs/2401.01692

0
arXiv - CSCL

MLPs Compass: What is learned when MLPs are combined with PLMs?. (arXiv:2401.01667v1 [cs.CL]) 

arxiv.org/abs/2401.01667

0
arXiv - CSCL

Social Media Ready Caption Generation for Brands. (arXiv:2401.01637v1 [cs.CL]) 

arxiv.org/abs/2401.01637

0
arXiv - CSCL

Can AI Be as Creative as Humans?. (arXiv:2401.01623v1 [cs.AI]) 

arxiv.org/abs/2401.01623

0
arXiv - CSCL

Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication. (arXiv:2401.01620v1 [cs.AI]) 

arxiv.org/abs/2401.01620

0
arXiv - CSCL

GPT-4V(ision) is a Generalist Web Agent, if Grounded. (arXiv:2401.01614v1 [cs.IR]) 

arxiv.org/abs/2401.01614

0
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy