Show newer
arXiv - CSCL

Is Information Extraction Solved by ChatGPT? An Analysis of Performance, Evaluation Criteria, Robustness and Errors. (arXiv:2305.14450v1 [cs.CL]) 

arxiv.org/abs/2305.14450

0
arXiv - CSCL

Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions. (arXiv:2305.14441v1 [cs.CL]) 

arxiv.org/abs/2305.14441

0
arXiv - CSCL

Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction. (arXiv:2305.14434v1 [cs.CL]) 

arxiv.org/abs/2305.14434

0
arXiv - CSCL

Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach. (arXiv:2305.14410v1 [cs.CV]) 

arxiv.org/abs/2305.14410

0
arXiv - CSCL

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback. (arXiv:2305.14387v1 [cs.LG]) 

arxiv.org/abs/2305.14387

0
arXiv - CSCL

Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation. (arXiv:2305.14386v1 [cs.LG]) 

arxiv.org/abs/2305.14386

0
arXiv - CSCL

Finding the Pillars of Strength for Multi-Head Attention. (arXiv:2305.14380v1 [cs.LG]) 

arxiv.org/abs/2305.14380

0
arXiv - CSCL

ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models. (arXiv:2210.04325v3 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2210.04325

0
arXiv - CSCL

Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection. (arXiv:2305.13276v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13276

0
arXiv - CSCL

SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations. (arXiv:2305.13235v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.13235

0
arXiv - CSCL

GPT-SW3: An Autoregressive Language Model for the Nordic Languages. (arXiv:2305.12987v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12987

0
arXiv - CSCL

Beyond Words: A Comprehensive Survey of Sentence Representations. (arXiv:2305.12641v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12641

0
arXiv - CSCL

Multilingual Simplification of Medical Texts. (arXiv:2305.12532v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12532

0
arXiv - CSCL

Evaluating the Performance of Large Language Models on GAOKAO Benchmark. (arXiv:2305.12474v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12474

0
arXiv - CSCL

Hedges in Bidirectional Translations of Publicity-Oriented Documents. (arXiv:2305.12146v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12146

0
arXiv - CSCL

How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings. (arXiv:2305.11853v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11853

0
arXiv - CSCL

Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses. (arXiv:2305.11662v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11662

0
arXiv - CSCL

Learning In-context Learning for Named Entity Recognition. (arXiv:2305.11038v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11038

0
arXiv - CSCL

Language Models Meet World Models: Embodied Experiences Enhance Language Models. (arXiv:2305.10626v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10626

0
arXiv - CSCL

A Better Way to Do Masked Language Model Scoring. (arXiv:2305.10588v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10588

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