Show newer
arXiv - CSCL

CONA: A novel CONtext-Aware instruction paradigm for communication using large language model. (arXiv:2305.18620v1 [cs.CL]) 

arxiv.org/abs/2305.18620

0
arXiv - CSCL

Likelihood-Based Diffusion Language Models. (arXiv:2305.18619v1 [cs.CL]) 

arxiv.org/abs/2305.18619

0
arXiv - CSCL

Chatbots put to the test in math and logic problems: A preliminary comparison and assessment of ChatGPT-3.5, ChatGPT-4, and Google Bard. (arXiv:2305.18618v1 [cs.CL]) 

arxiv.org/abs/2305.18618

0
arXiv - CSCL

From `Snippet-lects' to Doculects and Dialects: Leveraging Neural Representations of Speech for Placing Audio Signals in a Language Landscape. (arXiv:2305.18602v1 [cs.CL]) 

arxiv.org/abs/2305.18602

0
arXiv - CSCL

Improving Generalization for Multimodal Fake News Detection. (arXiv:2305.18599v1 [cs.CL]) 

arxiv.org/abs/2305.18599

0
arXiv - CSCL

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces. (arXiv:2305.18598v1 [cs.CL]) 

arxiv.org/abs/2305.18598

0
arXiv - CSCL

Building Accurate Low Latency ASR for Streaming Voice Search. (arXiv:2305.18596v1 [cs.SD]) 

arxiv.org/abs/2305.18596

0
arXiv - CSCL

Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models. (arXiv:2305.18585v1 [cs.CL]) 

arxiv.org/abs/2305.18585

0
arXiv - CSCL

Self Information Update for Large Language Models through Mitigating Exposure Bias. (arXiv:2305.18582v1 [cs.CL]) 

arxiv.org/abs/2305.18582

0
arXiv - CSCL

TreeMAN: Tree-enhanced Multimodal Attention Network for ICD Coding. (arXiv:2305.18576v1 [cs.CL]) 

arxiv.org/abs/2305.18576

0
arXiv - CSCL

Fairness of ChatGPT. (arXiv:2305.18569v1 [cs.LG]) 

arxiv.org/abs/2305.18569

0
arXiv - CSCL

PaLI-X: On Scaling up a Multilingual Vision and Language Model. (arXiv:2305.18565v1 [cs.CV]) 

arxiv.org/abs/2305.18565

0
arXiv - CSCL

Forgotten Knowledge: Examining the Citational Amnesia in NLP. (arXiv:2305.18554v1 [cs.CL]) 

arxiv.org/abs/2305.18554

0
arXiv - CSCL

SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics. (arXiv:2305.18513v1 [cs.CL]) 

arxiv.org/abs/2305.18513

0
arXiv - CSCL

Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models. (arXiv:2305.18507v1 [cs.CL]) 

arxiv.org/abs/2305.18507

0
arXiv - CSCL

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework. (arXiv:2305.18503v1 [cs.CL]) 

arxiv.org/abs/2305.18503

0
arXiv - CSCL

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset. (arXiv:2305.18500v1 [cs.CV]) 

arxiv.org/abs/2305.18500

0
arXiv - CSCL

ANPL: Compiling Natural Programs with Interactive Decomposition. (arXiv:2305.18498v1 [cs.PL]) 

arxiv.org/abs/2305.18498

0
arXiv - CSCL

A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets. (arXiv:2305.18486v1 [cs.CL]) 

arxiv.org/abs/2305.18486

0
arXiv - CSCL

Test-Time Training on Nearest Neighbors for Large Language Models. (arXiv:2305.18466v1 [cs.CL]) 

arxiv.org/abs/2305.18466

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