Show newer
arXiv - CSCL

A Categorical Archive of ChatGPT Failures. (arXiv:2302.03494v3 [cs.CL] UPDATED) 

arxiv.org/abs/2302.03494

0
arXiv - CSCL

Languages are Rewards: Chain of Hindsight Finetuning using Human Feedback. (arXiv:2302.02676v2 [cs.LG] UPDATED) 

arxiv.org/abs/2302.02676

0
arXiv - CSCL

Large Language Models Can Be Easily Distracted by Irrelevant Context. (arXiv:2302.00093v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.00093

0
arXiv - CSCL

Execution-based Code Generation using Deep Reinforcement Learning. (arXiv:2301.13816v2 [cs.LG] UPDATED) 

arxiv.org/abs/2301.13816

0
arXiv - CSCL

The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. (arXiv:2301.13688v2 [cs.AI] UPDATED) 

arxiv.org/abs/2301.13688

0
arXiv - CSCL

The 2022 n2c2/UW Shared Task on Extracting Social Determinants of Health. (arXiv:2301.05571v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.05571

0
arXiv - CSCL

Emergent Linguistic Structures in Neural Networks are Fragile. (arXiv:2210.17406v6 [cs.LG] UPDATED) 

arxiv.org/abs/2210.17406

0
arXiv - CSCL

Contrastive Search Is What You Need For Neural Text Generation. (arXiv:2210.14140v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.14140

0
arXiv - CSCL

DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models. (arXiv:2210.08933v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.08933

0
arXiv - CSCL

Contrastive Multimodal Learning for Emergence of Graphical Sensory-Motor Communication. (arXiv:2210.06468v2 [cs.AI] UPDATED) 

arxiv.org/abs/2210.06468

0
arXiv - CSCL

Like a bilingual baby: The advantage of visually grounding a bilingual language model. (arXiv:2210.05487v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.05487

0
arXiv - CSCL

Parameter-Efficient Tuning with Special Token Adaptation. (arXiv:2210.04382v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.04382

0
arXiv - CSCL

How people talk about each other: Modeling Generalized Intergroup Bias and Emotion. (arXiv:2209.06687v3 [cs.CL] UPDATED) 

arxiv.org/abs/2209.06687

0
arXiv - CSCL

Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems. (arXiv:2209.03755v3 [cs.CR] UPDATED) 

arxiv.org/abs/2209.03755

0
arXiv - CSCL

Focus-Driven Contrastive Learniang for Medical Question Summarization. (arXiv:2209.00484v3 [cs.CL] UPDATED) 

arxiv.org/abs/2209.00484

0
arXiv - CSCL

Transformers with Learnable Activation Functions. (arXiv:2208.14111v3 [cs.CL] UPDATED) 

arxiv.org/abs/2208.14111

0
arXiv - CSCL

Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies. (arXiv:2208.10264v4 [cs.CL] UPDATED) 

arxiv.org/abs/2208.10264

0
arXiv - CSCL

RevUp: Revise and Update Information Bottleneck for Event Representation. (arXiv:2205.12248v2 [cs.LG] UPDATED) 

arxiv.org/abs/2205.12248

0
arXiv - CSCL

QASem Parsing: Text-to-text Modeling of QA-based Semantics. (arXiv:2205.11413v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.11413

0
arXiv - CSCL

How Many Data Samples is an Additional Instruction Worth?. (arXiv:2203.09161v3 [cs.CL] UPDATED) 

arxiv.org/abs/2203.09161

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