Show newer
arXiv - CSCL

GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions. (arXiv:2310.15405v1 [cs.CL]) 

arxiv.org/abs/2310.15405

0
arXiv - CSCL

"One-size-fits-all"? Observations and Expectations of NLG Systems Across Identity-Related Language Features. (arXiv:2310.15398v1 [cs.CL]) 

arxiv.org/abs/2310.15398

0
arXiv - CSCL

DoGE: Domain Reweighting with Generalization Estimation. (arXiv:2310.15393v1 [cs.LG]) 

arxiv.org/abs/2310.15393

0
arXiv - CSCL

Irreducible Curriculum for Language Model Pretraining. (arXiv:2310.15389v1 [cs.CL]) 

arxiv.org/abs/2310.15389

0
arXiv - CSCL

GD-COMET: A Geo-Diverse Commonsense Inference Model. (arXiv:2310.15383v1 [cs.CL]) 

arxiv.org/abs/2310.15383

0
arXiv - CSCL

Semantic Data Management in Data Lakes. (arXiv:2310.15373v1 [cs.DB]) 

arxiv.org/abs/2310.15373

0
arXiv - CSCL

EpiK-Eval: Evaluation for Language Models as Epistemic Models. (arXiv:2310.15372v1 [cs.CL]) 

arxiv.org/abs/2310.15372

0
arXiv - CSCL

Why LLMs Hallucinate, and How to Get (Evidential) Closure: Perceptual, Intensional, and Extensional Learning for Faithful Natural Language Generation. (arXiv:2310.15355v1 [cs.CL]) 

arxiv.org/abs/2310.15355

0
arXiv - CSCL

Moral Foundations of Large Language Models. (arXiv:2310.15337v1 [cs.AI]) 

arxiv.org/abs/2310.15337

0
arXiv - CSCL

Specialist or Generalist? Instruction Tuning for Specific NLP Tasks. (arXiv:2310.15326v1 [cs.CL]) 

arxiv.org/abs/2310.15326

0
arXiv - CSCL

LXMERT Model Compression for Visual Question Answering. (arXiv:2310.15325v1 [cs.CV]) 

arxiv.org/abs/2310.15325

0
arXiv - CSCL

Hallucination Detection for Grounded Instruction Generation. (arXiv:2310.15319v1 [cs.CL]) 

arxiv.org/abs/2310.15319

0
arXiv - CSCL

Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses. (arXiv:2310.15317v1 [cs.CL]) 

arxiv.org/abs/2310.15317

0
arXiv - CSCL

Probing Representations for Document-level Event Extraction. (arXiv:2310.15316v1 [cs.CL]) 

arxiv.org/abs/2310.15316

0
arXiv - CSCL

Toward a Critical Toponymy Framework for Named Entity Recognition: A Case Study of Airbnb in New York City. (arXiv:2310.15302v1 [cs.CL]) 

arxiv.org/abs/2310.15302

0
arXiv - CSCL

TaskDiff: A Similarity Metric for Task-Oriented Conversations. (arXiv:2310.15298v1 [cs.CL]) 

arxiv.org/abs/2310.15298

0
arXiv - CSCL

DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM. (arXiv:2310.15296v1 [cs.CL]) 

arxiv.org/abs/2310.15296

0
arXiv - CSCL

Adaptive End-to-End Metric Learning for Zero-Shot Cross-Domain Slot Filling. (arXiv:2310.15294v1 [cs.CL]) 

arxiv.org/abs/2310.15294

0
arXiv - CSCL

On the Dimensionality of Sentence Embeddings. (arXiv:2310.15285v1 [cs.CL]) 

arxiv.org/abs/2310.15285

0
arXiv - CSCL

Efficient Algorithms for Recognizing Weighted Tree-Adjoining Languages. (arXiv:2310.15276v1 [cs.CL]) 

arxiv.org/abs/2310.15276

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