Show newer
arXiv - CSCL

Enhancing the Rationale-Input Alignment for Self-explaining Rationalization. (arXiv:2312.04103v1 [cs.AI]) 

arxiv.org/abs/2312.04103

0
arXiv - CSCL

Making Translators Privacy-aware on the User's Side. (arXiv:2312.04068v1 [cs.CR]) 

arxiv.org/abs/2312.04068

0
arXiv - CSCL

Comparing Large Language Model AI and Human-Generated Coaching Messages for Behavioral Weight Loss. (arXiv:2312.04059v1 [cs.CL]) 

arxiv.org/abs/2312.04059

0
arXiv - CSCL

Multimodal Misinformation Detection in a South African Social Media Environment. (arXiv:2312.04052v1 [cs.CL]) 

arxiv.org/abs/2312.04052

0
arXiv - CSCL

RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training. (arXiv:2312.04032v1 [cs.CL]) 

arxiv.org/abs/2312.04032

0
arXiv - CSCL

A Study on the Calibration of In-context Learning. (arXiv:2312.04021v1 [cs.CL]) 

arxiv.org/abs/2312.04021

0
arXiv - CSCL

Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration. (arXiv:2312.03987v1 [cs.CL]) 

arxiv.org/abs/2312.03987

0
arXiv - CSCL

Collaboration or Corporate Capture? Quantifying NLP's Reliance on Industry Artifacts and Contributions. (arXiv:2312.03912v1 [cs.CL]) 

arxiv.org/abs/2312.03912

0
arXiv - CSCL

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints. (arXiv:2312.03905v1 [cs.LG]) 

arxiv.org/abs/2312.03905

0
arXiv - CSCL

Revisiting the Optimality of Word Lengths. (arXiv:2312.03897v1 [cs.CL]) 

arxiv.org/abs/2312.03897

0
arXiv - CSCL

The BigCode Project Governance Card. (arXiv:2312.03872v1 [cs.CY]) 

arxiv.org/abs/2312.03872

0
arXiv - CSCL

Efficient Large Language Models: A Survey. (arXiv:2312.03863v1 [cs.CL]) 

arxiv.org/abs/2312.03863

0
arXiv - CSCL

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want. (arXiv:2312.03818v1 [cs.CV]) 

arxiv.org/abs/2312.03818

0
arXiv - CSCL

LLM as OS (llmao), Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem. (arXiv:2312.03815v1 [cs.OS]) 

arxiv.org/abs/2312.03815

0
arXiv - CSCL

Improving Activation Steering in Language Models with Mean-Centring. (arXiv:2312.03813v1 [cs.CL]) 

arxiv.org/abs/2312.03813

0
arXiv - CSCL

Comparative Analysis of Multilingual Text Classification & Identification through Deep Learning and Embedding Visualization. (arXiv:2312.03789v1 [cs.CL]) 

arxiv.org/abs/2312.03789

0
arXiv - CSCL

SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM. (arXiv:2312.03788v1 [cs.LG]) 

arxiv.org/abs/2312.03788

0
arXiv - CSCL

GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Science. (arXiv:2312.03769v1 [cs.CL]) 

arxiv.org/abs/2312.03769

0
arXiv - CSCL

Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment. (arXiv:2312.03766v1 [cs.CL]) 

arxiv.org/abs/2312.03766

0
arXiv - CSCL

How should the advent of large language models affect the practice of science?. (arXiv:2312.03759v1 [cs.CL]) 

arxiv.org/abs/2312.03759

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