Show newer
arXiv - CSCL

Large Language Models Are Reasoning Teachers. (arXiv:2212.10071v1 [cs.CL]) 

arxiv.org/abs/2212.10071

0
arXiv - CSCL

An AI Dungeon Master's Guide: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons. (arXiv:2212.10060v1 [cs.CL]) 

arxiv.org/abs/2212.10060

0
arXiv - CSCL

WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning. (arXiv:2212.10057v1 [cs.CL]) 

arxiv.org/abs/2212.10057

0
arXiv - CSCL

A Framework of Customer Review Analysis Using the Aspect-Based Opinion Mining Approach. (arXiv:2212.10051v1 [cs.CL]) 

arxiv.org/abs/2212.10051

0
arXiv - CSCL

An Augmentation Strategy for Visually Rich Documents. (arXiv:2212.10047v1 [cs.CL]) 

arxiv.org/abs/2212.10047

0
arXiv - CSCL

A Twitter BERT Approach for Offensive Language Detection in Marathi. (arXiv:2212.10039v1 [cs.CL]) 

arxiv.org/abs/2212.10039

0
arXiv - CSCL

Do language models have coherent mental models of everyday things?. (arXiv:2212.10029v1 [cs.CL]) 

arxiv.org/abs/2212.10029

0
arXiv - CSCL

When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods. (arXiv:2212.10025v1 [cs.LG]) 

arxiv.org/abs/2212.10025

0
arXiv - CSCL

On the Blind Spots of Model-Based Evaluation Metrics for Text Generation. (arXiv:2212.10020v1 [cs.CL]) 

arxiv.org/abs/2212.10020

0
arXiv - CSCL

When Do Decompositions Help for Machine Reading?. (arXiv:2212.10019v1 [cs.CL]) 

arxiv.org/abs/2212.10019

0
arXiv - CSCL

DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization. (arXiv:2212.10018v1 [cs.CL]) 

arxiv.org/abs/2212.10018

0
arXiv - CSCL

Benchmarking Spatial Relationships in Text-to-Image Generation. (arXiv:2212.10015v1 [cs.CV]) 

arxiv.org/abs/2212.10015

0
arXiv - CSCL

DocAsRef: A Pilot Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely. (arXiv:2212.10013v1 [cs.AI]) 

arxiv.org/abs/2212.10013

0
arXiv - CSCL

Language Modeling with Latent Situations. (arXiv:2212.10012v1 [cs.CL]) 

arxiv.org/abs/2212.10012

0
arXiv - CSCL

PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English. (arXiv:2212.10011v1 [cs.CL]) 

arxiv.org/abs/2212.10011

0
arXiv - CSCL

Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog. (arXiv:2212.10008v1 [cs.CL]) 

arxiv.org/abs/2212.10008

0
arXiv - CSCL

CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context. (arXiv:2212.10007v1 [cs.CL]) 

arxiv.org/abs/2212.10007

0
arXiv - CSCL

(QA)$^2$: Question Answering with Questionable Assumptions. (arXiv:2212.10003v1 [cs.CL]) 

arxiv.org/abs/2212.10003

0
arXiv - CSCL

Defending Against Poisoning Attacks in Open-Domain Question Answering. (arXiv:2212.10002v1 [cs.CL]) 

arxiv.org/abs/2212.10002

0
arXiv - CSCL

Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters. (arXiv:2212.10001v1 [cs.CL]) 

arxiv.org/abs/2212.10001

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