Show newer
arXiv - CSCL

Structured information extraction from complex scientific text with fine-tuned large language models. (arXiv:2212.05238v1 [cs.CL]) 

arxiv.org/abs/2212.05238

0
arXiv - CSCL

LEAD: Liberal Feature-based Distillation for Dense Retrieval. (arXiv:2212.05225v1 [cs.IR]) 

arxiv.org/abs/2212.05225

0
arXiv - CSCL

Machine intuition: Uncovering human-like intuitive decision-making in GPT-3.5. (arXiv:2212.05206v1 [cs.CL]) 

arxiv.org/abs/2212.05206

0
arXiv - CSCL

Artificial Text Detection with Multiple Training Strategies. (arXiv:2212.05194v1 [cs.CL]) 

arxiv.org/abs/2212.05194

0
arXiv - CSCL

Multi-task Learning for Personal Health Mention Detection on Social Media. (arXiv:2212.05147v1 [cs.CL]) 

arxiv.org/abs/2212.05147

0
arXiv - CSCL

Plug-and-Play Recipe Generation with Content Planning. (arXiv:2212.05093v1 [cs.CL]) 

arxiv.org/abs/2212.05093

0
arXiv - CSCL

A Generative Approach for Script Event Prediction via Contrastive Fine-tuning. (arXiv:2212.03496v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.03496

0
arXiv - CSCL

Legal Prompting: Teaching a Language Model to Think Like a Lawyer. (arXiv:2212.01326v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.01326

0
arXiv - CSCL

AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization. (arXiv:2212.00921v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.00921

0
arXiv - CSCL

Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models. (arXiv:2211.08682v3 [cs.CL] UPDATED) 

arxiv.org/abs/2211.08682

0
arXiv - CSCL

GMP*: Well-Tuned Gradual Magnitude Pruning Can Outperform Most BERT-Pruning Methods. (arXiv:2210.06384v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.06384

0
arXiv - CSCL

Detecting Spam Reviews on Vietnamese E-commerce Websites. (arXiv:2207.14636v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.14636

0
arXiv - CSCL

LogiGAN: Learning Logical Reasoning via Adversarial Pre-training. (arXiv:2205.08794v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.08794

0
arXiv - CSCL

ProQA: Structural Prompt-based Pre-training for Unified Question Answering. (arXiv:2205.04040v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.04040

0
arXiv - CSCL

Mixed-effects transformers for hierarchical adaptation. (arXiv:2205.01749v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.01749

0
arXiv - CSCL

Study of Indian English Pronunciation Variabilities relative to Received Pronunciation. (arXiv:2204.06502v2 [cs.CL] UPDATED) 

arxiv.org/abs/2204.06502

0
arXiv - CSCL

Learning to Transpile AMR into SPARQL. (arXiv:2112.07877v2 [cs.CL] UPDATED) 

arxiv.org/abs/2112.07877

0
arXiv - CSCL

Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization. (arXiv:2111.01528v3 [cs.CL] UPDATED) 

arxiv.org/abs/2111.01528

0
arXiv - CSCL

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. (arXiv:2212.05055v1 [cs.LG]) 

arxiv.org/abs/2212.05055

0
arXiv - CSCL

Incorporating Emotions into Health Mention Classification Task on Social Media. (arXiv:2212.05039v1 [cs.CL]) 

arxiv.org/abs/2212.05039

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