Show newer
arXiv - CSCL

Proceedings of the 3rd International Workshop on Mining and Learning in the Legal Domain (MLLD-23). (arXiv:2311.10733v1 [cs.CY]) 

arxiv.org/abs/2311.10733

0
arXiv - CSCL

Chatbot-supported Thesis Writing: An Autoethnographic Report. (arXiv:2311.10729v1 [cs.CY]) 

arxiv.org/abs/2311.10729

0
arXiv - CSCL

Large Language Models in Finance: A Survey. (arXiv:2311.10723v1 [q-fin.GN]) 

arxiv.org/abs/2311.10723

0
arXiv - CSCL

PsyBench: a balanced and in-depth Psychological Chinese Evaluation Benchmark for Foundation Models. (arXiv:2311.09861v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.09861

0
arXiv - CSCL

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering. (arXiv:2311.06668v2 [cs.LG] UPDATED) 

arxiv.org/abs/2311.06668

0
arXiv - CSCL

Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models. (arXiv:2311.06233v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.06233

0
arXiv - CSCL

Uncovering Intermediate Variables in Transformers using Circuit Probing. (arXiv:2311.04354v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04354

0
arXiv - CSCL

DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking. (arXiv:2310.18075v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.18075

0
arXiv - CSCL

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion. (arXiv:2310.11248v2 [cs.LG] UPDATED) 

arxiv.org/abs/2310.11248

0
arXiv - CSCL

Targeted Image Data Augmentation Increases Basic Skills Captioning Robustness. (arXiv:2309.15991v2 [cs.CV] UPDATED) 

arxiv.org/abs/2309.15991

0
arXiv - CSCL

Insights Into the Nutritional Prevention of Macular Degeneration based on a Comparative Topic Modeling Approach. (arXiv:2309.00312v4 [cs.CL] UPDATED) 

arxiv.org/abs/2309.00312

0
arXiv - CSCL

VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use. (arXiv:2308.06595v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.06595

0
arXiv - CSCL

Who Wrote this Code? Watermarking for Code Generation. (arXiv:2305.15060v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15060

0
arXiv - CSCL

A Fair and In-Depth Evaluation of Existing End-to-End Entity Linking Systems. (arXiv:2305.14937v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14937

0
arXiv - CSCL

InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction. (arXiv:2305.14659v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14659

0
arXiv - CSCL

Hierarchical Catalogue Generation for Literature Review: A Benchmark. (arXiv:2304.03512v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.03512

0
arXiv - CSCL

GPT-4 can pass the Korean National Licensing Examination for Korean Medicine Doctors. (arXiv:2303.17807v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.17807

0
arXiv - CSCL

Language Models can Solve Computer Tasks. (arXiv:2303.17491v3 [cs.CL] UPDATED) 

arxiv.org/abs/2303.17491

0
arXiv - CSCL

Classifying COVID-19 vaccine narratives. (arXiv:2207.08522v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.08522

0
arXiv - CSCL

Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Search. (arXiv:2203.08436v2 [cs.CL] UPDATED) 

arxiv.org/abs/2203.08436

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