Show newer
arXiv - CSCL

Enhancing Long-form Text Generation Efficacy with Task-adaptive Tokenization. (arXiv:2310.05317v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05317

0
arXiv - CSCL

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems. (arXiv:2310.05280v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05280

0
arXiv - CSCL

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models. (arXiv:2310.05074v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05074

0
arXiv - CSCL

Guideline Learning for In-context Information Extraction. (arXiv:2310.05066v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05066

0
arXiv - CSCL

Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU. (arXiv:2310.04928v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.04928

0
arXiv - CSCL

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model. (arXiv:2310.04445v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.04445

0
arXiv - CSCL

Evaluating Hallucinations in Chinese Large Language Models. (arXiv:2310.03368v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.03368

0
arXiv - CSCL

Conversational Health Agents: A Personalized LLM-Powered Agent Framework. (arXiv:2310.02374v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02374

0
arXiv - CSCL

Improving Dialogue Management: Quality Datasets vs Models. (arXiv:2310.01339v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.01339

0
arXiv - CSCL

GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond. (arXiv:2309.16583v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.16583

0
arXiv - CSCL

Prompt Tuned Embedding Classification for Multi-Label Industry Sector Allocation. (arXiv:2309.12075v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.12075

0
arXiv - CSCL

Towards Effective Disambiguation for Machine Translation with Large Language Models. (arXiv:2309.11668v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.11668

0
arXiv - CSCL

Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts. (arXiv:2309.07430v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.07430

0
arXiv - CSCL

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL. (arXiv:2309.06553v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.06553

0
arXiv - CSCL

One Wide Feedforward is All You Need. (arXiv:2309.01826v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.01826

0
arXiv - CSCL

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. (arXiv:2308.13137v2 [cs.LG] UPDATED) 

arxiv.org/abs/2308.13137

0
arXiv - CSCL

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors. (arXiv:2308.10848v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.10848

0
arXiv - CSCL

End-to-End Evaluation for Low-Latency Simultaneous Speech Translation. (arXiv:2308.03415v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.03415

0
arXiv - CSCL

Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models. (arXiv:2308.01684v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.01684

0
arXiv - CSCL

Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes. (arXiv:2307.15455v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.15455

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