Show newer
arXiv - CSCL

In-context Learning and Gradient Descent Revisited. (arXiv:2311.07772v1 [cs.CL]) 

arxiv.org/abs/2311.07772

0
arXiv - CSCL

GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization. (arXiv:2311.07767v1 [cs.CL]) 

arxiv.org/abs/2311.07767

0
arXiv - CSCL

Vision-Language Integration in Multimodal Video Transformers (Partially) Aligns with the Brain. (arXiv:2311.07766v1 [cs.CV]) 

arxiv.org/abs/2311.07766

0
arXiv - CSCL

Generalization Analogies (GENIES): A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains. (arXiv:2311.07723v1 [cs.AI]) 

arxiv.org/abs/2311.07723

0
arXiv - CSCL

PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature. (arXiv:2311.07715v1 [cs.CL]) 

arxiv.org/abs/2311.07715

0
arXiv - CSCL

Measuring Entrainment in Spontaneous Code-switched Speech. (arXiv:2311.07703v1 [cs.CL]) 

arxiv.org/abs/2311.07703

0
arXiv - CSCL

AuthentiGPT: Detecting Machine-Generated Text via Black-Box Language Models Denoising. (arXiv:2311.07700v1 [cs.CL]) 

arxiv.org/abs/2311.07700

0
arXiv - CSCL

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models. (arXiv:2311.07692v1 [cs.LG]) 

arxiv.org/abs/2311.07692

0
arXiv - CSCL

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming. (arXiv:2311.07689v1 [cs.CL]) 

arxiv.org/abs/2311.07689

0
arXiv - CSCL

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games. (arXiv:2311.07687v1 [cs.CL]) 

arxiv.org/abs/2311.07687

0
arXiv - CSCL

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion. (arXiv:2311.07682v1 [cs.CL]) 

arxiv.org/abs/2311.07682

0
arXiv - CSCL

Past as a Guide: Leveraging Retrospective Learning for Python Code Completion. (arXiv:2311.07635v1 [cs.SE]) 

arxiv.org/abs/2311.07635

0
arXiv - CSCL

Large Language Models' Understanding of Math: Source Criticism and Extrapolation. (arXiv:2311.07618v1 [cs.LG]) 

arxiv.org/abs/2311.07618

0
arXiv - CSCL

CLAMP: A Contrastive Language And Molecule Pre-training Network. (arXiv:2311.07617v1 [cs.CL]) 

arxiv.org/abs/2311.07617

0
arXiv - CSCL

Intentional Biases in LLM Responses. (arXiv:2311.07611v1 [cs.CL]) 

arxiv.org/abs/2311.07611

0
arXiv - CSCL

Multi-Label Topic Model for Financial Textual Data. (arXiv:2311.07598v1 [q-fin.ST]) 

arxiv.org/abs/2311.07598

0
arXiv - CSCL

How to Bridge the Gap between Modalities: A Comprehensive Survey on Multimodal Large Language Model. (arXiv:2311.07594v1 [cs.CL]) 

arxiv.org/abs/2311.07594

0
arXiv - CSCL

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification. (arXiv:2311.07593v1 [cs.CL]) 

arxiv.org/abs/2311.07593

0
arXiv - CSCL

Hallucination-minimized Data-to-answer Framework for Financial Decision-makers. (arXiv:2311.07592v1 [cs.CL]) 

arxiv.org/abs/2311.07592

0
arXiv - CSCL

Identification of Books That are Suitable for Middle School Students Using Artificial Neural Networks. (arXiv:2311.07591v1 [cs.CL]) 

arxiv.org/abs/2311.07591

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy