Show newer
arXiv - CSCL

Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity. (arXiv:2305.02176v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.02176

0
arXiv - CSCL

GPT-RE: In-context Learning for Relation Extraction using Large Language Models. (arXiv:2305.02105v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.02105

0
arXiv - CSCL

Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation. (arXiv:2305.01498v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.01498

0
arXiv - CSCL

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models. (arXiv:2305.01219v5 [cs.CL] UPDATED) 

arxiv.org/abs/2305.01219

0
arXiv - CSCL

Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4. (arXiv:2305.00118v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.00118

0
arXiv - CSCL

Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens. (arXiv:2304.11389v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.11389

0
arXiv - CSCL

Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling. (arXiv:2304.09145v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.09145

0
arXiv - CSCL

Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing. (arXiv:2304.08315v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.08315

0
arXiv - CSCL

MEGA: Multilingual Evaluation of Generative AI. (arXiv:2303.12528v4 [cs.CL] UPDATED) 

arxiv.org/abs/2303.12528

0
arXiv - CSCL

Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization. (arXiv:2303.12314v4 [cs.CL] UPDATED) 

arxiv.org/abs/2303.12314

0
arXiv - CSCL

Context-faithful Prompting for Large Language Models. (arXiv:2303.11315v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.11315

0
arXiv - CSCL

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!. (arXiv:2303.08559v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.08559

0
arXiv - CSCL

WiCE: Real-World Entailment for Claims in Wikipedia. (arXiv:2303.01432v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.01432

0
arXiv - CSCL

AI Chat Assistants can Improve Conversations about Divisive Topics. (arXiv:2302.07268v5 [cs.HC] UPDATED) 

arxiv.org/abs/2302.07268

0
arXiv - CSCL

Towards Agile Text Classifiers for Everyone. (arXiv:2302.06541v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.06541

0
arXiv - CSCL

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning. (arXiv:2302.04858v2 [cs.CV] UPDATED) 

arxiv.org/abs/2302.04858

0
arXiv - CSCL

CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. (arXiv:2302.04012v2 [cs.CR] UPDATED) 

arxiv.org/abs/2302.04012

0
arXiv - CSCL

Concept Algebra for Score-Based Conditional Models. (arXiv:2302.03693v3 [cs.CL] UPDATED) 

arxiv.org/abs/2302.03693

0
arXiv - CSCL

Using In-Context Learning to Improve Dialogue Safety. (arXiv:2302.00871v3 [cs.CL] UPDATED) 

arxiv.org/abs/2302.00871

0
arXiv - CSCL

Knowledge Distillation $\approx$ Label Smoothing: Fact or Fallacy?. (arXiv:2301.12609v3 [cs.LG] UPDATED) 

arxiv.org/abs/2301.12609

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