Show newer
arXiv - CSCL

Revisiting Automated Prompting: Are We Actually Doing Better?. (arXiv:2304.03609v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.03609

0
arXiv - CSCL

Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results. (arXiv:2303.04715v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.04715

0
arXiv - CSCL

Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction. (arXiv:2301.09209v3 [cs.CV] UPDATED) 

arxiv.org/abs/2301.09209

0
arXiv - CSCL

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. (arXiv:2212.10509v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10509

0
arXiv - CSCL

A Natural Bias for Language Generation Models. (arXiv:2212.09686v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.09686

0
arXiv - CSCL

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions. (arXiv:2207.00746v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.00746

0
arXiv - CSCL

Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting. (arXiv:2110.05367v2 [cs.CL] UPDATED) 

arxiv.org/abs/2110.05367

0
arXiv - CSCL

Determinantal Beam Search. (arXiv:2106.07400v4 [cs.CL] UPDATED) 

arxiv.org/abs/2106.07400

0
arXiv - CSCL

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. (arXiv:2306.13651v1 [cs.CL]) 

arxiv.org/abs/2306.13651

0
arXiv - CSCL

GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models. (arXiv:2306.13649v1 [cs.LG]) 

arxiv.org/abs/2306.13649

0
arXiv - CSCL

Margin Maximization in Attention Mechanism. (arXiv:2306.13596v1 [cs.LG]) 

arxiv.org/abs/2306.13596

0
arXiv - CSCL

System-Level Natural Language Feedback. (arXiv:2306.13588v1 [cs.CL]) 

arxiv.org/abs/2306.13588

0
arXiv - CSCL

A Survey on Multimodal Large Language Models. (arXiv:2306.13549v1 [cs.CV]) 

arxiv.org/abs/2306.13549

0
arXiv - CSCL

Knowledge-Infused Self Attention Transformers. (arXiv:2306.13501v1 [cs.CL]) 

arxiv.org/abs/2306.13501

0
arXiv - CSCL

Incorporating Graph Information in Transformer-based AMR Parsing. (arXiv:2306.13467v1 [cs.CL]) 

arxiv.org/abs/2306.13467

0
arXiv - CSCL

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation. (arXiv:2306.13460v1 [cs.CL]) 

arxiv.org/abs/2306.13460

0
arXiv - CSCL

Long-range Language Modeling with Self-retrieval. (arXiv:2306.13421v1 [cs.CL]) 

arxiv.org/abs/2306.13421

0
arXiv - CSCL

Stress Testing BERT Anaphora Resolution Models for Reaction Extraction in Chemical Patents. (arXiv:2306.13379v1 [cs.CL]) 

arxiv.org/abs/2306.13379

0
arXiv - CSCL

Abstractive Text Summarization for Resumes With Cutting Edge NLP Transformers and LSTM. (arXiv:2306.13315v1 [cs.CL]) 

arxiv.org/abs/2306.13315

0
arXiv - CSCL

Mutually Guided Few-shot Learning for Relational Triple Extraction. (arXiv:2306.13310v1 [cs.CL]) 

arxiv.org/abs/2306.13310

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