Show newer
arXiv - CSCL

Spider4SPARQL: A Complex Benchmark for Evaluating Knowledge Graph Question Answering Systems. (arXiv:2309.16248v1 [cs.CL]) 

arxiv.org/abs/2309.16248

0
arXiv - CSCL

Language models in molecular discovery. (arXiv:2309.16235v1 [physics.chem-ph]) 

arxiv.org/abs/2309.16235

0
arXiv - CSCL

Analyzing Political Figures in Real-Time: Leveraging YouTube Metadata for Sentiment Analysis. (arXiv:2309.16234v1 [cs.CL]) 

arxiv.org/abs/2309.16234

0
arXiv - CSCL

Controllable Text Generation with Residual Memory Transformer. (arXiv:2309.16231v1 [cs.CL]) 

arxiv.org/abs/2309.16231

0
arXiv - CSCL

Brand Network Booster: A New System for Improving Brand Connectivity. (arXiv:2309.16228v1 [cs.SI]) 

arxiv.org/abs/2309.16228

0
arXiv - CSCL

Marathi-English Code-mixed Text Generation. (arXiv:2309.16202v1 [cs.CL]) 

arxiv.org/abs/2309.16202

0
arXiv - CSCL

Using Weak Supervision and Data Augmentation in Question Answering. (arXiv:2309.16175v1 [cs.CL]) 

arxiv.org/abs/2309.16175

0
arXiv - CSCL

Large Language Model Soft Ideologization via AI-Self-Consciousness. (arXiv:2309.16167v1 [cs.CL]) 

arxiv.org/abs/2309.16167

0
arXiv - CSCL

The Trickle-down Impact of Reward (In-)consistency on RLHF. (arXiv:2309.16155v1 [cs.CL]) 

arxiv.org/abs/2309.16155

0
arXiv - CSCL

AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events. (arXiv:2309.16150v1 [cs.CL]) 

arxiv.org/abs/2309.16150

0
arXiv - CSCL

The Confidence-Competence Gap in Large Language Models: A Cognitive Study. (arXiv:2309.16145v1 [cs.CL]) 

arxiv.org/abs/2309.16145

0
arXiv - CSCL

TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration. (arXiv:2309.16090v1 [cs.AI]) 

arxiv.org/abs/2309.16090

0
arXiv - CSCL

Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble. (arXiv:2309.16082v1 [cs.CL]) 

arxiv.org/abs/2309.16082

0
arXiv - CSCL

AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model. (arXiv:2309.16058v1 [cs.LG]) 

arxiv.org/abs/2309.16058

0
arXiv - CSCL

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods. (arXiv:2309.16042v1 [cs.LG]) 

arxiv.org/abs/2309.16042

0
arXiv - CSCL

Effective Long-Context Scaling of Foundation Models. (arXiv:2309.16039v1 [cs.CL]) 

arxiv.org/abs/2309.16039

0
arXiv - CSCL

MedEdit: Model Editing for Medical Question Answering with External Knowledge Bases. (arXiv:2309.16035v1 [cs.CL]) 

arxiv.org/abs/2309.16035

0
arXiv - CSCL

Targeted Image Data Augmentation Increases Basic Skills Captioning Robustness. (arXiv:2309.15991v1 [cs.CV]) 

arxiv.org/abs/2309.15991

0
arXiv - CSCL

Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project. (arXiv:2309.15869v1 [cs.CL]) 

arxiv.org/abs/2309.15869

0
arXiv - CSCL

A Survey on Image-text Multimodal Models. (arXiv:2309.15857v1 [cs.CL]) 

arxiv.org/abs/2309.15857

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