Show newer
arXiv - CSCL

Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales. (arXiv:2312.07399v1 [cs.CL]) 

arxiv.org/abs/2312.07399

0
arXiv - CSCL

LLMEval: A Preliminary Study on How to Evaluate Large Language Models. (arXiv:2312.07398v1 [cs.AI]) 

arxiv.org/abs/2312.07398

0
arXiv - CSCL

A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames. (arXiv:2312.07395v1 [cs.CV]) 

arxiv.org/abs/2312.07395

0
arXiv - CSCL

Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification. (arXiv:2312.07338v1 [cs.CL]) 

arxiv.org/abs/2312.07338

0
arXiv - CSCL

SCCA: Shifted Cross Chunk Attention for long contextual semantic expansion. (arXiv:2312.07305v1 [cs.CL]) 

arxiv.org/abs/2312.07305

0
arXiv - CSCL

Towards Equipping Transformer with the Ability of Systematic Compositionality. (arXiv:2312.07280v1 [cs.CL]) 

arxiv.org/abs/2312.07280

0
arXiv - CSCL

GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction. (arXiv:2312.07255v1 [cs.CL]) 

arxiv.org/abs/2312.07255

0
arXiv - CSCL

The GUA-Speech System Description for CNVSRC Challenge 2023. (arXiv:2312.07254v1 [cs.CL]) 

arxiv.org/abs/2312.07254

0
arXiv - CSCL

Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning. (arXiv:2312.07250v1 [cs.CL]) 

arxiv.org/abs/2312.07250

0
arXiv - CSCL

Toxic language detection: a systematic survey of Arabic datasets. (arXiv:2312.07228v1 [cs.CL]) 

arxiv.org/abs/2312.07228

0
arXiv - CSCL

Verbreitungsmechanismen sch\"adigender Sprache im Netz: Anatomie zweier Shitstorms. (arXiv:2312.07194v1 [cs.CL]) 

arxiv.org/abs/2312.07194

0
arXiv - CSCL

Classifying complex documents: comparing bespoke solutions to large language models. (arXiv:2312.07182v1 [cs.CL]) 

arxiv.org/abs/2312.07182

0
arXiv - CSCL

Multilingual large language models leak human stereotypes across language boundaries. (arXiv:2312.07141v1 [cs.CL]) 

arxiv.org/abs/2312.07141

0
arXiv - CSCL

LLMs Perform Poorly at Concept Extraction in Cyber-security Research Literature. (arXiv:2312.07110v1 [cs.CL]) 

arxiv.org/abs/2312.07110

0
arXiv - CSCL

BED: Bi-Encoder-Decoder Model for Canonical Relation Extraction. (arXiv:2312.07088v1 [cs.CL]) 

arxiv.org/abs/2312.07088

0
arXiv - CSCL

Context Matter: Data-Efficient Augmentation of Large Language Models for Scientific Applications. (arXiv:2312.07069v1 [cs.CL]) 

arxiv.org/abs/2312.07069

0
arXiv - CSCL

DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models. (arXiv:2312.07066v1 [cs.CL]) 

arxiv.org/abs/2312.07066

0
arXiv - CSCL

Improving Factual Error Correction by Learning to Inject Factual Errors. (arXiv:2312.07049v1 [cs.CL]) 

arxiv.org/abs/2312.07049

0
arXiv - CSCL

Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models. (arXiv:2312.07046v1 [cs.LG]) 

arxiv.org/abs/2312.07046

0
arXiv - CSCL

Dynamic Corrective Self-Distillation for Better Fine-Tuning of Pretrained Models. (arXiv:2312.07028v1 [cs.CL]) 

arxiv.org/abs/2312.07028

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