Show newer
arXiv - CSCL

Less is More for Long Document Summary Evaluation by LLMs. (arXiv:2309.07382v1 [cs.CL]) 

arxiv.org/abs/2309.07382

0
arXiv - CSCL

Hybrid Attention-based Encoder-decoder Model for Efficient Language Model Adaptation. (arXiv:2309.07369v1 [eess.AS]) 

arxiv.org/abs/2309.07369

0
arXiv - CSCL

Learning from Auxiliary Sources in Argumentative Revision Classification. (arXiv:2309.07334v1 [cs.CL]) 

arxiv.org/abs/2309.07334

0
arXiv - CSCL

Traveling Words: A Geometric Interpretation of Transformers. (arXiv:2309.07315v1 [cs.CL]) 

arxiv.org/abs/2309.07315

0
arXiv - CSCL

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs. (arXiv:2309.07311v1 [cs.CL]) 

arxiv.org/abs/2309.07311

0
arXiv - CSCL

In-Contextual Bias Suppression for Large Language Models. (arXiv:2309.07251v1 [cs.CL]) 

arxiv.org/abs/2309.07251

0
arXiv - CSCL

Exploring Large Language Models for Ontology Alignment. (arXiv:2309.07172v1 [cs.AI]) 

arxiv.org/abs/2309.07172

0
arXiv - CSCL

AKEM: Aligning Knowledge Base to Queries with Ensemble Model for Entity Recognition and Linking. (arXiv:2309.06175v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.06175

0
arXiv - CSCL

Stochastic LLMs do not Understand Language: Towards Symbolic, Explainable and Ontologically Based LLMs. (arXiv:2309.05918v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.05918

0
arXiv - CSCL

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models. (arXiv:2309.05605v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.05605

0
arXiv - CSCL

NExT-GPT: Any-to-Any Multimodal LLM. (arXiv:2309.05519v2 [cs.AI] UPDATED) 

arxiv.org/abs/2309.05519

0
arXiv - CSCL

Understanding the Impact of Post-Training Quantization on Large Language Models. (arXiv:2309.05210v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.05210

0
arXiv - CSCL

ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning. (arXiv:2309.01538v2 [cs.AI] UPDATED) 

arxiv.org/abs/2309.01538

0
arXiv - CSCL

A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages. (arXiv:2308.09435v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.09435

0
arXiv - CSCL

SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability. (arXiv:2308.03266v3 [cs.SD] UPDATED) 

arxiv.org/abs/2308.03266

0
arXiv - CSCL

Scaling Relationship on Learning Mathematical Reasoning with Large Language Models. (arXiv:2308.01825v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.01825

0
arXiv - CSCL

GRDD: A Dataset for Greek Dialectal NLP. (arXiv:2308.00802v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.00802

0
arXiv - CSCL

Findings of Factify 2: Multimodal Fake News Detection. (arXiv:2307.10475v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.10475

0
arXiv - CSCL

A Comprehensive Overview of Large Language Models. (arXiv:2307.06435v3 [cs.CL] UPDATED) 

arxiv.org/abs/2307.06435

0
arXiv - CSCL

Cross-corpus Readability Compatibility Assessment for English Texts. (arXiv:2306.09704v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.09704

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