Show newer
arXiv - CSCL

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts. (arXiv:2212.10543v1 [cs.CL]) 

arxiv.org/abs/2212.10543

0
arXiv - CSCL

Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?. (arXiv:2212.10539v1 [cs.CL]) 

arxiv.org/abs/2212.10539

0
arXiv - CSCL

Does CLIP Bind Concepts? Probing Compositionality in Large Image Models. (arXiv:2212.10537v1 [cs.CV]) 

arxiv.org/abs/2212.10537

0
arXiv - CSCL

Measure More, Question More: Experimental Studies on Transformer-based Language Models and Complement Coercion. (arXiv:2212.10536v1 [cs.CL]) 

arxiv.org/abs/2212.10536

0
arXiv - CSCL

A Survey of Deep Learning for Mathematical Reasoning. (arXiv:2212.10535v1 [cs.AI]) 

arxiv.org/abs/2212.10535

0
arXiv - CSCL

DISCO: Distilling Phrasal Counterfactuals with Large Language Models. (arXiv:2212.10534v1 [cs.CL]) 

arxiv.org/abs/2212.10534

0
arXiv - CSCL

Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective. (arXiv:2212.10529v1 [cs.CL]) 

arxiv.org/abs/2212.10529

0
arXiv - CSCL

HYRR: Hybrid Infused Reranking for Passage Retrieval. (arXiv:2212.10528v1 [cs.CL]) 

arxiv.org/abs/2212.10528

0
arXiv - CSCL

Exploring the Challenges of Open Domain Multi-Document Summarization. (arXiv:2212.10526v1 [cs.CL]) 

arxiv.org/abs/2212.10526

0
arXiv - CSCL

SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks. (arXiv:2212.10525v1 [cs.CL]) 

arxiv.org/abs/2212.10525

0
arXiv - CSCL

Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End. (arXiv:2212.10522v1 [cs.CL]) 

arxiv.org/abs/2212.10522

0
arXiv - CSCL

Privacy-Preserving Domain Adaptation of Semantic Parsers. (arXiv:2212.10520v1 [cs.CL]) 

arxiv.org/abs/2212.10520

0
arXiv - CSCL

CausalDialogue: Modeling Utterance-level Causality in Conversations. (arXiv:2212.10515v1 [cs.CL]) 

arxiv.org/abs/2212.10515

0
arXiv - CSCL

When Not to Trust Language Models: Investigating Effectiveness and Limitations of Parametric and Non-Parametric Memories. (arXiv:2212.10511v1 [cs.CL]) 

arxiv.org/abs/2212.10511

0
arXiv - CSCL

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. (arXiv:2212.10509v1 [cs.CL]) 

arxiv.org/abs/2212.10509

0
arXiv - CSCL

DePlot: One-shot visual language reasoning by plot-to-table translation. (arXiv:2212.10505v1 [cs.CL]) 

arxiv.org/abs/2212.10505

0
arXiv - CSCL

Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?. (arXiv:2212.10504v1 [cs.CL]) 

arxiv.org/abs/2212.10504

0
arXiv - CSCL

Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training. (arXiv:2212.10503v1 [cs.CL]) 

arxiv.org/abs/2212.10503

0
arXiv - CSCL

A Measure-Theoretic Characterization of Tight Language Models. (arXiv:2212.10502v1 [cs.CL]) 

arxiv.org/abs/2212.10502

0
arXiv - CSCL

SimpleStyle: An Adaptable Style Transfer Approach. (arXiv:2212.10498v1 [cs.CL]) 

arxiv.org/abs/2212.10498

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