Show newer
arXiv - CSCL

Combining Transfer Learning with In-context Learning using Blackbox LLMs for Zero-shot Knowledge Base Question Answering. (arXiv:2311.08894v1 [cs.CL]) 

arxiv.org/abs/2311.08894

0
arXiv - CSCL

Large Language Models are legal but they are not: Making the case for a powerful LegalLLM. (arXiv:2311.08890v1 [cs.CL]) 

arxiv.org/abs/2311.08890

0
arXiv - CSCL

CLIMB: Curriculum Learning for Infant-inspired Model Building. (arXiv:2311.08886v1 [cs.CL]) 

arxiv.org/abs/2311.08886

0
arXiv - CSCL

Enabling Large Language Models to Learn from Rules. (arXiv:2311.08883v1 [cs.CL]) 

arxiv.org/abs/2311.08883

0
arXiv - CSCL

Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation. (arXiv:2311.08877v1 [cs.CL]) 

arxiv.org/abs/2311.08877

0
arXiv - CSCL

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining. (arXiv:2311.08849v1 [cs.CL]) 

arxiv.org/abs/2311.08849

0
arXiv - CSCL

Violet: A Vision-Language Model for Arabic Image Captioning with Gemini Decoder. (arXiv:2311.08844v1 [cs.CV]) 

arxiv.org/abs/2311.08844

0
arXiv - CSCL

Disinformation Capabilities of Large Language Models. (arXiv:2311.08838v1 [cs.CL]) 

arxiv.org/abs/2311.08838

0
arXiv - CSCL

Evaluating Gender Bias in the Translation of Gender-Neutral Languages into English. (arXiv:2311.08836v1 [cs.CL]) 

arxiv.org/abs/2311.08836

0
arXiv - CSCL

MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy. (arXiv:2311.08817v1 [cs.CL]) 

arxiv.org/abs/2311.08817

0
arXiv - CSCL

StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving. (arXiv:2311.08803v1 [cs.CL]) 

arxiv.org/abs/2311.08803

0
arXiv - CSCL

German FinBERT: A German Pre-trained Language Model. (arXiv:2311.08793v1 [cs.CL]) 

arxiv.org/abs/2311.08793

0
arXiv - CSCL

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects. (arXiv:2311.08788v1 [cs.CL]) 

arxiv.org/abs/2311.08788

0
arXiv - CSCL

Three Conjectures on Unexpectedeness. (arXiv:2311.08768v1 [cs.AI]) 

arxiv.org/abs/2311.08768

0
arXiv - CSCL

Accelerating Toeplitz Neural Network with Constant-time Inference Complexity. (arXiv:2311.08756v1 [cs.CL]) 

arxiv.org/abs/2311.08756

0
arXiv - CSCL

Thread of Thought Unraveling Chaotic Contexts. (arXiv:2311.08734v1 [cs.CL]) 

arxiv.org/abs/2311.08734

0
arXiv - CSCL

Enhancing Emergency Decision-making with Knowledge Graphs and Large Language Models. (arXiv:2311.08732v1 [cs.CL]) 

arxiv.org/abs/2311.08732

0
arXiv - CSCL

Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission. (arXiv:2311.08726v1 [cs.CL]) 

arxiv.org/abs/2311.08726

0
arXiv - CSCL

Method for Text Entity Linking in Power Distribution Scheduling Oriented to Power Distribution Network Knowledge Graph. (arXiv:2311.08724v1 [cs.CL]) 

arxiv.org/abs/2311.08724

0
arXiv - CSCL

Token Prediction as Implicit Classification to Identify LLM-Generated Text. (arXiv:2311.08723v1 [cs.CL]) 

arxiv.org/abs/2311.08723

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