Show newer
arXiv - CSCL

On the Representational Capacity of Recurrent Neural Language Models. (arXiv:2310.12942v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12942

0
arXiv - CSCL

A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models. (arXiv:2310.12936v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12936

0
arXiv - CSCL

StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding. (arXiv:2310.12874v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12874

0
arXiv - CSCL

AgentTuning: Enabling Generalized Agent Abilities for LLMs. (arXiv:2310.12823v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12823

0
arXiv - CSCL

Towards Real-World Streaming Speech Translation for Code-Switched Speech. (arXiv:2310.12648v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12648

0
arXiv - CSCL

Pretraining Language Models with Text-Attributed Heterogeneous Graphs. (arXiv:2310.12580v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12580

0
arXiv - CSCL

Towards Safer Operations: An Expert-involved Dataset of High-Pressure Gas Incidents for Preventing Future Failures. (arXiv:2310.12074v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12074

0
arXiv - CSCL

Evaluating the Symbol Binding Ability of Large Language Models for Multiple-Choice Questions in Vietnamese General Education. (arXiv:2310.12059v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12059

0
arXiv - CSCL

LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation. (arXiv:2310.12020v2 [cs.RO] UPDATED) 

arxiv.org/abs/2310.12020

0
arXiv - CSCL

Fast Multipole Attention: A Divide-and-Conquer Attention Mechanism for Long Sequences. (arXiv:2310.11960v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11960

0
arXiv - CSCL

From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification. (arXiv:2310.11878v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11878

0
arXiv - CSCL

Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling. (arXiv:2310.11772v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11772

0
arXiv - CSCL

VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights. (arXiv:2310.11368v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11368

0
arXiv - CSCL

VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System. (arXiv:2310.11069v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.11069

0
arXiv - CSCL

Emergent AI-Assisted Discourse: Case Study of a Second Language Writer Authoring with ChatGPT. (arXiv:2310.10903v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10903

0
arXiv - CSCL

BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys. (arXiv:2310.10765v3 [cs.CV] UPDATED) 

arxiv.org/abs/2310.10765

0
arXiv - CSCL

Theory of Mind for Multi-Agent Collaboration via Large Language Models. (arXiv:2310.10701v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10701

0
arXiv - CSCL

Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation. (arXiv:2310.10698v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10698

0
arXiv - CSCL

In-Context Pretraining: Language Modeling Beyond Document Boundaries. (arXiv:2310.10638v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10638

0
arXiv - CSCL

RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling. (arXiv:2310.10567v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10567

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