Show newer
arXiv - CSCL

CoSiNES: Contrastive Siamese Network for Entity Standardization. (arXiv:2306.03316v1 [cs.CL]) 

arxiv.org/abs/2306.03316

0
arXiv - CSCL

Few Shot Rationale Generation using Self-Training with Dual Teachers. (arXiv:2306.03315v1 [cs.CL]) 

arxiv.org/abs/2306.03315

0
arXiv - CSCL

A Scalable and Adaptive System to Infer the Industry Sectors of Companies: Prompt + Model Tuning of Generative Language Models. (arXiv:2306.03313v1 [cs.CL]) 

arxiv.org/abs/2306.03313

0
arXiv - CSCL

Stack Over-Flowing with Results: The Case for Domain-Specific Pre-Training Over One-Size-Fits-All Models. (arXiv:2306.03268v1 [cs.CL]) 

arxiv.org/abs/2306.03268

0
arXiv - CSCL

shs-nlp at RadSum23: Domain-Adaptive Pre-training of Instruction-tuned LLMs for Radiology Report Impression Generation. (arXiv:2306.03264v1 [cs.CL]) 

arxiv.org/abs/2306.03264

0
arXiv - CSCL

Understanding the Effectiveness of Early Weight Averaging for Training Large Language Models. (arXiv:2306.03241v1 [cs.LG]) 

arxiv.org/abs/2306.03241

0
arXiv - CSCL

NLU on Data Diets: Dynamic Data Subset Selection for NLP Classification Tasks. (arXiv:2306.03208v1 [cs.CL]) 

arxiv.org/abs/2306.03208

0
arXiv - CSCL

A Static Evaluation of Code Completion by Large Language Models. (arXiv:2306.03203v1 [cs.CL]) 

arxiv.org/abs/2306.03203

0
arXiv - CSCL

AutoScrum: Automating Project Planning Using Large Language Models. (arXiv:2306.03197v1 [cs.AI]) 

arxiv.org/abs/2306.03197

0
arXiv - CSCL

Easy-to-Read in Germany: A Survey on its Current State and Available Resources. (arXiv:2306.03189v1 [cs.CL]) 

arxiv.org/abs/2306.03189

0
arXiv - CSCL

Composition and Deformance: Measuring Imageability with a Text-to-Image Model. (arXiv:2306.03168v1 [cs.CL]) 

arxiv.org/abs/2306.03168

0
arXiv - CSCL

Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training. (arXiv:2306.03166v1 [cs.IR]) 

arxiv.org/abs/2306.03166

0
arXiv - CSCL

Sampling and Ranking for Digital Ink Generation on a tight computational budget. (arXiv:2306.03103v1 [cs.HC]) 

arxiv.org/abs/2306.03103

0
arXiv - CSCL

ChatGPT is a Remarkable Tool -- For Experts. (arXiv:2306.03102v1 [cs.HC]) 

arxiv.org/abs/2306.03102

0
arXiv - CSCL

Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT. (arXiv:2306.01393v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.01393

0
arXiv - CSCL

Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction. (arXiv:2306.00418v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.00418

0
arXiv - CSCL

A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets. (arXiv:2305.18486v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18486

0
arXiv - CSCL

In-Context Analogical Reasoning with Pre-Trained Language Models. (arXiv:2305.17626v2 [cs.AI] UPDATED) 

arxiv.org/abs/2305.17626

0
arXiv - CSCL

Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark. (arXiv:2305.17553v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.17553

0
arXiv - CSCL

Answering Unanswered Questions through Semantic Reformulations in Spoken QA. (arXiv:2305.17393v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.17393

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