Show newer
arXiv - CSCL

UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction. (arXiv:2401.05689v1 [cs.CL]) 

arxiv.org/abs/2401.05689

0
arXiv - CSCL

ConcEPT: Concept-Enhanced Pre-Training for Language Models. (arXiv:2401.05669v1 [cs.CL]) 

arxiv.org/abs/2401.05669

0
arXiv - CSCL

Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability. (arXiv:2401.05655v1 [cs.CL]) 

arxiv.org/abs/2401.05655

0
arXiv - CSCL

Towards Conversational Diagnostic AI. (arXiv:2401.05654v1 [cs.AI]) 

arxiv.org/abs/2401.05654

0
arXiv - CSCL

On Detecting Cherry-picking in News Coverage Using Large Language Models. (arXiv:2401.05650v1 [cs.CL]) 

arxiv.org/abs/2401.05650

0
arXiv - CSCL

Natural Language Processing for Dialects of a Language: A Survey. (arXiv:2401.05632v1 [cs.CL]) 

arxiv.org/abs/2401.05632

0
arXiv - CSCL

DrawTalking: Building Interactive Worlds by Sketching and Speaking. (arXiv:2401.05631v1 [cs.HC]) 

arxiv.org/abs/2401.05631

0
arXiv - CSCL

The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models. (arXiv:2401.05618v1 [cs.CL]) 

arxiv.org/abs/2401.05618

0
arXiv - CSCL

Scaling Laws for Forgetting When Fine-Tuning Large Language Models. (arXiv:2401.05605v1 [cs.CL]) 

arxiv.org/abs/2401.05605

0
arXiv - CSCL

REBUS: A Robust Evaluation Benchmark of Understanding Symbols. (arXiv:2401.05604v1 [cs.CL]) 

arxiv.org/abs/2401.05604

0
arXiv - CSCL

POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation. (arXiv:2401.05596v1 [cs.CL]) 

arxiv.org/abs/2401.05596

0
arXiv - CSCL

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. (arXiv:2401.05566v1 [cs.CR]) 

arxiv.org/abs/2401.05566

0
arXiv - CSCL

TrustLLM: Trustworthiness in Large Language Models. (arXiv:2401.05561v1 [cs.CL]) 

arxiv.org/abs/2401.05561

0
arXiv - CSCL

Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?. (arXiv:2401.05551v1 [cs.CL]) 

arxiv.org/abs/2401.05551

0
arXiv - CSCL

CodePrompt: Improving Source Code-Related Classification with Knowledge Features through Prompt Learning. (arXiv:2401.05544v1 [cs.CL]) 

arxiv.org/abs/2401.05544

0
arXiv - CSCL

From Pampas to Pixels: Fine-Tuning Diffusion Models for Ga\'ucho Heritage. (arXiv:2401.05520v1 [cs.CV]) 

arxiv.org/abs/2401.05520

0
arXiv - CSCL

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks. (arXiv:2401.05507v1 [cs.CL]) 

arxiv.org/abs/2401.05507

0
arXiv - CSCL

LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems. (arXiv:2401.05443v1 [cs.SE]) 

arxiv.org/abs/2401.05443

0
arXiv - CSCL

Enhancing Essay Scoring with Adversarial Weights Perturbation and Metric-specific AttentionPooling. (arXiv:2401.05433v1 [cs.CL]) 

arxiv.org/abs/2401.05433

0
arXiv - CSCL

Automated Assessment of Students' Code Comprehension using LLMs. (arXiv:2401.05399v1 [cs.CY]) 

arxiv.org/abs/2401.05399

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