Show newer
arXiv - CSCL

Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure. (arXiv:2311.07590v1 [cs.CL]) 

arxiv.org/abs/2311.07590

0
arXiv - CSCL

Dialogizer: Context-aware Conversational-QA Dataset Generation from Textual Sources. (arXiv:2311.07589v1 [cs.CL]) 

arxiv.org/abs/2311.07589

0
arXiv - CSCL

NLQxform: A Language Model-based Question to SPARQL Transformer. (arXiv:2311.07588v1 [cs.CL]) 

arxiv.org/abs/2311.07588

0
arXiv - CSCL

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?. (arXiv:2311.07587v1 [cs.CL]) 

arxiv.org/abs/2311.07587

0
arXiv - CSCL

Input Reconstruction Attack against Vertical Federated Large Language Models. (arXiv:2311.07585v1 [cs.CL]) 

arxiv.org/abs/2311.07585

0
arXiv - CSCL

Performance Prediction of Data-Driven Knowledge summarization of High Entropy Alloys (HEAs) literature implementing Natural Language Processing algorithms. (arXiv:2311.07584v1 [cs.CL]) 

arxiv.org/abs/2311.07584

0
arXiv - CSCL

Cross-Dialect Sentence Transformation: A Comparative Analysis of Language Models for Adapting Sentences to British English. (arXiv:2311.07583v1 [cs.CL]) 

arxiv.org/abs/2311.07583

0
arXiv - CSCL

Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions. (arXiv:2311.07582v1 [cs.CL]) 

arxiv.org/abs/2311.07582

0
arXiv - CSCL

Time Travel in LLMs: Tracing Data Contamination in Large Language Models. (arXiv:2308.08493v2 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2308.08493

0
arXiv - CSCL

Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming in the Wild. (arXiv:2311.06237v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.06237

0
arXiv - CSCL

Removing RLHF Protections in GPT-4 via Fine-Tuning. (arXiv:2311.05553v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.05553

0
arXiv - CSCL

An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach. (arXiv:2311.04913v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04913

0
arXiv - CSCL

Rethinking Benchmark and Contamination for Language Models with Rephrased Samples. (arXiv:2311.04850v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04850

0
arXiv - CSCL

NExT-Chat: An LMM for Chat, Detection and Segmentation. (arXiv:2311.04498v3 [cs.CV] UPDATED) 

arxiv.org/abs/2311.04498

0
arXiv - CSCL

ChaTA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs. (arXiv:2311.02775v2 [cs.LG] UPDATED) 

arxiv.org/abs/2311.02775

0
arXiv - CSCL

Citance-Contextualized Summarization of Scientific Papers. (arXiv:2311.02408v3 [cs.CL] UPDATED) 

arxiv.org/abs/2311.02408

0
arXiv - CSCL

Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models. (arXiv:2311.01732v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.01732

0
arXiv - CSCL

Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization. (arXiv:2311.01544v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.01544

0
arXiv - CSCL

AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models. (arXiv:2311.01305v3 [cs.LG] UPDATED) 

arxiv.org/abs/2311.01305

0
arXiv - CSCL

COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances. (arXiv:2311.01012v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.01012

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