Show newer
arXiv - CSCL

LLM aided semi-supervision for Extractive Dialog Summarization. (arXiv:2311.11462v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.11462

0
arXiv - CSCL

ProAgent: From Robotic Process Automation to Agentic Process Automation. (arXiv:2311.10751v2 [cs.RO] UPDATED) 

arxiv.org/abs/2311.10751

0
arXiv - CSCL

Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers. (arXiv:2311.10642v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.10642

0
arXiv - CSCL

The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation. (arXiv:2311.10057v3 [cs.SD] UPDATED) 

arxiv.org/abs/2311.10057

0
arXiv - CSCL

Backdoor Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment. (arXiv:2311.09433v2 [cs.CR] UPDATED) 

arxiv.org/abs/2311.09433

0
arXiv - CSCL

Input Reconstruction Attack against Vertical Federated Large Language Models. (arXiv:2311.07585v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07585

0
arXiv - CSCL

TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System. (arXiv:2311.06622v2 [cs.AI] UPDATED) 

arxiv.org/abs/2311.06622

0
arXiv - CSCL

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models. (arXiv:2311.06607v2 [cs.CV] UPDATED) 

arxiv.org/abs/2311.06607

0
arXiv - CSCL

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences. (arXiv:2311.06025v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.06025

0
arXiv - CSCL

Causal Inference from Text: Unveiling Interactions between Variables. (arXiv:2311.05286v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.05286

0
arXiv - CSCL

Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation. (arXiv:2311.03348v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.03348

0
arXiv - CSCL

PACuna: Automated Fine-Tuning of Language Models for Particle Accelerators. (arXiv:2310.19106v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.19106

0
arXiv - CSCL

She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models. (arXiv:2310.18333v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.18333

0
arXiv - CSCL

DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking. (arXiv:2310.18075v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.18075

0
arXiv - CSCL

Proving Test Set Contamination in Black Box Language Models. (arXiv:2310.17623v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.17623

0
arXiv - CSCL

Cultural and Linguistic Diversity Improves Visual Representations. (arXiv:2310.14356v2 [cs.CV] UPDATED) 

arxiv.org/abs/2310.14356

0
arXiv - CSCL

Exploration with Principles for Diverse AI Supervision. (arXiv:2310.08899v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.08899

0
arXiv - CSCL

Revisiting Large Language Models as Zero-shot Relation Extractors. (arXiv:2310.05028v4 [cs.AI] UPDATED) 

arxiv.org/abs/2310.05028

0
arXiv - CSCL

Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM. (arXiv:2310.04483v2 [cs.LG] UPDATED) 

arxiv.org/abs/2310.04483

0
arXiv - CSCL

Fewer is More: Trojan Attacks on Parameter-Efficient Fine-Tuning. (arXiv:2310.00648v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.00648

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