Show newer
arXiv - CSCL

Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks. (arXiv:2304.14732v5 [cs.CL] UPDATED) 

arxiv.org/abs/2304.14732

0
arXiv - CSCL

Improving Autoregressive NLP Tasks via Modular Linearized Attention. (arXiv:2304.08453v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.08453

0
arXiv - CSCL

Emergence of Symbols in Neural Networks for Semantic Understanding and Communication. (arXiv:2304.06377v3 [cs.AI] UPDATED) 

arxiv.org/abs/2304.06377

0
arXiv - CSCL

Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning. (arXiv:2304.01295v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.01295

0
arXiv - CSCL

ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge. (arXiv:2303.14070v5 [cs.CL] UPDATED) 

arxiv.org/abs/2303.14070

0
arXiv - CSCL

From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding. (arXiv:2303.12816v2 [cs.LG] UPDATED) 

arxiv.org/abs/2303.12816

0
arXiv - CSCL

Learning Transductions and Alignments with RNN Seq2seq Models. (arXiv:2303.06841v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.06841

0
arXiv - CSCL

SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks. (arXiv:2302.13939v3 [cs.CL] UPDATED) 

arxiv.org/abs/2302.13939

0
arXiv - CSCL

Sequential Query Encoding For Complex Query Answering on Knowledge Graphs. (arXiv:2302.13114v3 [cs.CL] UPDATED) 

arxiv.org/abs/2302.13114

0
arXiv - CSCL

Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues. (arXiv:2302.05895v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.05895

0
arXiv - CSCL

Perceive and predict: self-supervised speech representation based loss functions for speech enhancement. (arXiv:2301.04388v3 [cs.SD] UPDATED) 

arxiv.org/abs/2301.04388

0
arXiv - CSCL

Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions. (arXiv:2212.10189v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.10189

0
arXiv - CSCL

Diverse Demonstrations Improve In-context Compositional Generalization. (arXiv:2212.06800v3 [cs.CL] UPDATED) 

arxiv.org/abs/2212.06800

0
arXiv - CSCL

Prompting PaLM for Translation: Assessing Strategies and Performance. (arXiv:2211.09102v3 [cs.CL] UPDATED) 

arxiv.org/abs/2211.09102

0
arXiv - CSCL

Probing neural language models for understanding of words of estimative probability. (arXiv:2211.03358v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.03358

0
arXiv - CSCL

KSAT: Knowledge-infused Self Attention Transformer -- Integrating Multiple Domain-Specific Contexts. (arXiv:2210.04307v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.04307

0
arXiv - CSCL

PROD: Progressive Distillation for Dense Retrieval. (arXiv:2209.13335v3 [cs.IR] UPDATED) 

arxiv.org/abs/2209.13335

0
arXiv - CSCL

A Cognitive Study on Semantic Similarity Analysis of Large Corpora: A Transformer-based Approach. (arXiv:2207.11716v3 [cs.CL] UPDATED) 

arxiv.org/abs/2207.11716

0
arXiv - CSCL

Vision-and-Language Pretraining. (arXiv:2207.01772v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.01772

0
arXiv - CSCL

DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles. (arXiv:2207.01079v3 [cs.CL] UPDATED) 

arxiv.org/abs/2207.01079

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