Show newer
arXiv - CSCL

Rethinking Benchmark and Contamination for Language Models with Rephrased Samples. (arXiv:2311.04850v1 [cs.CL]) 

arxiv.org/abs/2311.04850

0
arXiv - CSCL

Hierarchically Gated Recurrent Neural Network for Sequence Modeling. (arXiv:2311.04823v1 [cs.CL]) 

arxiv.org/abs/2311.04823

0
arXiv - CSCL

MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document. (arXiv:2311.04816v1 [cs.CL]) 

arxiv.org/abs/2311.04816

0
arXiv - CSCL

DACBERT: Leveraging Dependency Agreement for Cost-Efficient Bert Pretraining. (arXiv:2311.04799v1 [cs.CL]) 

arxiv.org/abs/2311.04799

0
arXiv - CSCL

Determination of toxic comments and unintended model bias minimization using Deep learning approach. (arXiv:2311.04789v1 [cs.LG]) 

arxiv.org/abs/2311.04789

0
arXiv - CSCL

Using large language models to study human memory for meaningful narratives. (arXiv:2311.04742v1 [cs.CL]) 

arxiv.org/abs/2311.04742

0
arXiv - CSCL

Evaluating Generative Ad Hoc Information Retrieval. (arXiv:2311.04694v1 [cs.IR]) 

arxiv.org/abs/2311.04694

0
arXiv - CSCL

Pre-training LLMs using human-like development data corpus. (arXiv:2311.04666v1 [cs.CL]) 

arxiv.org/abs/2311.04666

0
arXiv - CSCL

Speech language models lack important brain-relevant semantics. (arXiv:2311.04664v1 [cs.CL]) 

arxiv.org/abs/2311.04664

0
arXiv - CSCL

Massive Editing for Large Language Models via Meta Learning. (arXiv:2311.04661v1 [cs.CL]) 

arxiv.org/abs/2311.04661

0
arXiv - CSCL

TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models. (arXiv:2311.04589v1 [cs.CL]) 

arxiv.org/abs/2311.04589

0
arXiv - CSCL

Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum. (arXiv:2311.04563v1 [cs.CL]) 

arxiv.org/abs/2311.04563

0
arXiv - CSCL

Assessing Distractors in Multiple-Choice Tests. (arXiv:2311.04554v1 [cs.CL]) 

arxiv.org/abs/2311.04554

0
arXiv - CSCL

Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures. (arXiv:2311.04547v1 [cs.CL]) 

arxiv.org/abs/2311.04547

0
arXiv - CSCL

RankAug: Augmented data ranking for text classification. (arXiv:2311.04535v1 [cs.CL]) 

arxiv.org/abs/2311.04535

0
arXiv - CSCL

Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token Based ASR. (arXiv:2311.04534v1 [cs.CL]) 

arxiv.org/abs/2311.04534

0
arXiv - CSCL

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction. (arXiv:2311.04507v1 [cs.CL]) 

arxiv.org/abs/2311.04507

0
arXiv - CSCL

NExT-Chat: An LMM for Chat, Detection and Segmentation. (arXiv:2311.04498v1 [cs.CV]) 

arxiv.org/abs/2311.04498

0
arXiv - CSCL

Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection. (arXiv:2311.04495v1 [cs.CL]) 

arxiv.org/abs/2311.04495

0
arXiv - CSCL

CLearViD: Curriculum Learning for Video Description. (arXiv:2311.04480v1 [cs.CV]) 

arxiv.org/abs/2311.04480

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy