Show newer
arXiv - CSCL

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs. (arXiv:2306.16601v1 [cs.LG]) 

arxiv.org/abs/2306.16601

0
arXiv - CSCL

Automatic Calibration and Error Correction for Large Language Models via Pareto Optimal Self-Supervision. (arXiv:2306.16564v1 [cs.CL]) 

arxiv.org/abs/2306.16564

0
arXiv - CSCL

ICSVR: Investigating Compositional and Semantic Understanding in Video Retrieval Models. (arXiv:2306.16533v1 [cs.CV]) 

arxiv.org/abs/2306.16533

0
arXiv - CSCL

Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering. (arXiv:2306.16478v1 [cs.IR]) 

arxiv.org/abs/2306.16478

0
arXiv - CSCL

A Framework for Identifying Depression on Social Media: MentalRiskES@IberLEF 2023. (arXiv:2306.16125v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.16125

0
arXiv - CSCL

Chain-of-Thought Prompt Distillation for Multimodal Named Entity and Multimodal Relation Extraction. (arXiv:2306.14122v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.14122

0
arXiv - CSCL

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. (arXiv:2306.13651v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.13651

0
arXiv - CSCL

Data Augmentation Approaches for Source Code Models: A Survey. (arXiv:2305.19915v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.19915

0
arXiv - CSCL

ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Task. (arXiv:2304.14177v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.14177

0
arXiv - CSCL

Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models. (arXiv:2304.07396v2 [cs.LG] UPDATED) 

arxiv.org/abs/2304.07396

0
arXiv - CSCL

A Survey of Large Language Models. (arXiv:2303.18223v11 [cs.CL] UPDATED) 

arxiv.org/abs/2303.18223

0
arXiv - CSCL

Can AI-Generated Text be Reliably Detected?. (arXiv:2303.11156v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.11156

0
arXiv - CSCL

Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data. (arXiv:2303.02577v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.02577

0
arXiv - CSCL

Predicting Sentence-Level Factuality of News and Bias of Media Outlets. (arXiv:2301.11850v3 [cs.CL] UPDATED) 

arxiv.org/abs/2301.11850

0
arXiv - CSCL

MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module. (arXiv:2301.07087v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.07087

0
arXiv - CSCL

Log-linear Guardedness and its Implications. (arXiv:2210.10012v2 [cs.LG] UPDATED) 

arxiv.org/abs/2210.10012

0
arXiv - CSCL

The expected sum of edge lengths in planar linearizations of trees. Theory and applications. (arXiv:2207.05564v3 [cs.CL] UPDATED) 

arxiv.org/abs/2207.05564

0
arXiv - CSCL

Language Models as Knowledge Embeddings. (arXiv:2206.12617v3 [cs.CL] UPDATED) 

arxiv.org/abs/2206.12617

0
arXiv - CSCL

On the Usefulness of Embeddings, Clusters and Strings for Text Generator Evaluation. (arXiv:2205.16001v4 [cs.CL] UPDATED) 

arxiv.org/abs/2205.16001

0
arXiv - CSCL

"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks. (arXiv:2204.04636v2 [cs.AI] UPDATED) 

arxiv.org/abs/2204.04636

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