Show newer
arXiv - CSCL

ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese. (arXiv:2309.02902v1 [cs.CL]) 

arxiv.org/abs/2309.02902

0
arXiv - CSCL

A deep Natural Language Inference predictor without language-specific training data. (arXiv:2309.02887v1 [cs.CL]) 

arxiv.org/abs/2309.02887

0
arXiv - CSCL

Aligning Large Language Models for Clinical Tasks. (arXiv:2309.02884v1 [cs.CL]) 

arxiv.org/abs/2309.02884

0
arXiv - CSCL

Promoting Open-domain Dialogue Generation through Learning Pattern Information between Contexts and Responses. (arXiv:2309.02823v1 [cs.CL]) 

arxiv.org/abs/2309.02823

0
arXiv - CSCL

Agent-based simulation of pedestrians' earthquake evacuation; application to Beirut, Lebanon. (arXiv:2309.02812v1 [cs.CL]) 

arxiv.org/abs/2309.02812

0
arXiv - CSCL

Norm Tweaking: High-performance Low-bit Quantization of Large Language Models. (arXiv:2309.02784v1 [cs.LG]) 

arxiv.org/abs/2309.02784

0
arXiv - CSCL

GRASS: Unified Generation Model for Speech Semantic Understanding. (arXiv:2309.02780v1 [cs.CL]) 

arxiv.org/abs/2309.02780

0
arXiv - CSCL

Improving Code Generation by Dynamic Temperature Sampling. (arXiv:2309.02772v1 [cs.SE]) 

arxiv.org/abs/2309.02772

0
arXiv - CSCL

Rubric-Specific Approach to Automated Essay Scoring with Augmentation Training. (arXiv:2309.02740v1 [cs.CL]) 

arxiv.org/abs/2309.02740

0
arXiv - CSCL

HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus. (arXiv:2309.02731v1 [cs.CL]) 

arxiv.org/abs/2309.02731

0
arXiv - CSCL

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery. (arXiv:2309.02726v1 [cs.CL]) 

arxiv.org/abs/2309.02726

0
arXiv - CSCL

Offensive Hebrew Corpus and Detection using BERT. (arXiv:2309.02724v1 [cs.CL]) 

arxiv.org/abs/2309.02724

0
arXiv - CSCL

HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models. (arXiv:2309.02706v1 [cs.CL]) 

arxiv.org/abs/2309.02706

0
arXiv - CSCL

Certifying LLM Safety against Adversarial Prompting. (arXiv:2309.02705v1 [cs.CL]) 

arxiv.org/abs/2309.02705

0
arXiv - CSCL

A Joint Study of Phrase Grounding and Task Performance in Vision and Language Models. (arXiv:2309.02691v1 [cs.CL]) 

arxiv.org/abs/2309.02691

0
arXiv - CSCL

Zero-Resource Hallucination Prevention for Large Language Models. (arXiv:2309.02654v1 [cs.CL]) 

arxiv.org/abs/2309.02654

0
arXiv - CSCL

Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation. (arXiv:2309.02640v1 [cs.LG]) 

arxiv.org/abs/2309.02640

0
arXiv - CSCL

Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning. (arXiv:2309.02591v1 [cs.LG]) 

arxiv.org/abs/2309.02591

0
arXiv - CSCL

Automating Behavioral Testing in Machine Translation. (arXiv:2309.02553v1 [cs.CL]) 

arxiv.org/abs/2309.02553

0
arXiv - CSCL

Minimal Effective Theory for Phonotactic Memory: Capturing Local Correlations due to Errors in Speech. (arXiv:2309.02466v1 [eess.AS]) 

arxiv.org/abs/2309.02466

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