Show newer
arXiv - CSCL

Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models. (arXiv:2310.13315v1 [cs.CL]) 

arxiv.org/abs/2310.13315

0
arXiv - CSCL

Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models. (arXiv:2310.13312v1 [cs.CL]) 

arxiv.org/abs/2310.13312

0
arXiv - CSCL

Test-Time Self-Adaptive Small Language Models for Question Answering. (arXiv:2310.13307v1 [cs.CL]) 

arxiv.org/abs/2310.13307

0
arXiv - CSCL

Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting. (arXiv:2310.13297v1 [cs.CL]) 

arxiv.org/abs/2310.13297

0
arXiv - CSCL

Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks. (arXiv:2310.13291v1 [cs.CL]) 

arxiv.org/abs/2310.13291

0
arXiv - CSCL

Interpreting Indirect Answers to Yes-No Questions in Multiple Languages. (arXiv:2310.13290v1 [cs.CL]) 

arxiv.org/abs/2310.13290

0
arXiv - CSCL

SALMONN: Towards Generic Hearing Abilities for Large Language Models. (arXiv:2310.13289v1 [cs.SD]) 

arxiv.org/abs/2310.13289

0
arXiv - CSCL

InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution. (arXiv:2310.13276v1 [cs.CV]) 

arxiv.org/abs/2310.13276

0
arXiv - CSCL

On the Language Encoder of Contrastive Cross-modal Models. (arXiv:2310.13267v1 [cs.CL]) 

arxiv.org/abs/2310.13267

0
arXiv - CSCL

MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model. (arXiv:2310.13265v1 [cs.CL]) 

arxiv.org/abs/2310.13265

0
arXiv - CSCL

A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation. (arXiv:2310.13262v1 [cs.CL]) 

arxiv.org/abs/2310.13262

0
arXiv - CSCL

Visual Grounding Helps Learn Word Meanings in Low-Data Regimes. (arXiv:2310.13257v1 [cs.CL]) 

arxiv.org/abs/2310.13257

0
arXiv - CSCL

Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches. (arXiv:2310.13247v1 [cs.CL]) 

arxiv.org/abs/2310.13247

0
arXiv - CSCL

Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking. (arXiv:2310.13243v1 [cs.IR]) 

arxiv.org/abs/2310.13243

0
arXiv - CSCL

Multi-level Contrastive Learning for Script-based Character Understanding. (arXiv:2310.13231v1 [cs.CL]) 

arxiv.org/abs/2310.13231

0
arXiv - CSCL

The Less the Merrier? Investigating Language Representation in Multilingual Models. (arXiv:2310.13228v1 [cs.CL]) 

arxiv.org/abs/2310.13228

0
arXiv - CSCL

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search. (arXiv:2310.13227v1 [cs.CL]) 

arxiv.org/abs/2310.13227

0
arXiv - CSCL

Enhancing Zero-Shot Crypto Sentiment with Fine-tuned Language Model and Prompt Engineering. (arXiv:2310.13226v1 [cs.CL]) 

arxiv.org/abs/2310.13226

0
arXiv - CSCL

MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition. (arXiv:2310.13213v1 [cs.CL]) 

arxiv.org/abs/2310.13213

0
arXiv - CSCL

Primacy Effect of ChatGPT. (arXiv:2310.13206v1 [cs.CL]) 

arxiv.org/abs/2310.13206

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