Show newer
arXiv - CSCL

Quality > Quantity: Synthetic Corpora from Foundation Models for Closed-Domain Extractive Question Answering. (arXiv:2310.16995v1 [cs.CL]) 

arxiv.org/abs/2310.16995

0
arXiv - CSCL

How well can machine-generated texts be identified and can language models be trained to avoid identification?. (arXiv:2310.16992v1 [cs.CL]) 

arxiv.org/abs/2310.16992

0
arXiv - CSCL

STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants. (arXiv:2310.16990v1 [cs.CL]) 

arxiv.org/abs/2310.16990

0
arXiv - CSCL

Understanding Social Structures from Contemporary Literary Fiction using Character Interaction Graph -- Half Century Chronology of Influential Bengali Writers. (arXiv:2310.16968v1 [cs.CL]) 

arxiv.org/abs/2310.16968

0
arXiv - CSCL

Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation. (arXiv:2310.16964v1 [cs.CL]) 

arxiv.org/abs/2310.16964

0
arXiv - CSCL

Zephyr: Direct Distillation of LM Alignment. (arXiv:2310.16944v1 [cs.LG]) 

arxiv.org/abs/2310.16944

0
arXiv - CSCL

Learning Transfers over Several Programming Languages. (arXiv:2310.16937v1 [cs.CL]) 

arxiv.org/abs/2310.16937

0
arXiv - CSCL

CL-MASR: A Continual Learning Benchmark for Multilingual ASR. (arXiv:2310.16931v1 [cs.CL]) 

arxiv.org/abs/2310.16931

0
arXiv - CSCL

Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errors. (arXiv:2310.16924v1 [cs.CL]) 

arxiv.org/abs/2310.16924

0
arXiv - CSCL

Divide et Impera: Multi-Transformer Architectures for Complex NLP-Tasks. (arXiv:2310.16897v1 [cs.CL]) 

arxiv.org/abs/2310.16897

0
arXiv - CSCL

DEFT: Data Efficient Fine-Tuning for Large Language Models via Unsupervised Core-Set Selection. (arXiv:2310.16776v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.16776

0
arXiv - CSCL

SkyMath: Technical Report. (arXiv:2310.16713v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.16713

0
arXiv - CSCL

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models. (arXiv:2310.16436v2 [cs.CV] UPDATED) 

arxiv.org/abs/2310.16436

0
arXiv - CSCL

Unraveling Feature Extraction Mechanisms in Neural Networks. (arXiv:2310.16350v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.16350

0
arXiv - CSCL

Knowledge Editing for Large Language Models: A Survey. (arXiv:2310.16218v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.16218

0
arXiv - CSCL

COPF: Continual Learning Human Preference through Optimal Policy Fitting. (arXiv:2310.15694v3 [cs.LG] UPDATED) 

arxiv.org/abs/2310.15694

0
arXiv - CSCL

Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model. (arXiv:2310.15113v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.15113

0
arXiv - CSCL

Can Language Models Laugh at YouTube Short-form Videos?. (arXiv:2310.14159v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.14159

0
arXiv - CSCL

Simultaneous Machine Translation with Tailored Reference. (arXiv:2310.13588v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.13588

0
arXiv - CSCL

Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding. (arXiv:2310.11191v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11191

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