Show newer
arXiv - CSCL

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models. (arXiv:2309.14717v1 [cs.LG] CROSS LISTED) 

arxiv.org/abs/2309.14717

0
arXiv - CSCL

Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shuffling. (arXiv:2309.06726v1 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2309.06726

0
arXiv - CSCL

Seeing and hearing what has not been said; A multimodal client behavior classifier in Motivational Interviewing with interpretable fusion. (arXiv:2309.14398v2 [cs.LG] UPDATED) 

arxiv.org/abs/2309.14398

0
arXiv - CSCL

ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning. (arXiv:2309.13701v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.13701

0
arXiv - CSCL

SLHCat: Mapping Wikipedia Categories and Lists to DBpedia by Leveraging Semantic, Lexical, and Hierarchical Features. (arXiv:2309.11791v2 [cs.DL] UPDATED) 

arxiv.org/abs/2309.11791

0
arXiv - CSCL

Are Large Language Models Really Robust to Word-Level Perturbations?. (arXiv:2309.11166v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.11166

0
arXiv - CSCL

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods. (arXiv:2309.10966v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.10966

0
arXiv - CSCL

Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation. (arXiv:2309.10677v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.10677

0
arXiv - CSCL

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs. (arXiv:2309.07311v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.07311

0
arXiv - CSCL

Cognitive Architectures for Language Agents. (arXiv:2309.02427v2 [cs.AI] UPDATED) 

arxiv.org/abs/2309.02427

0
arXiv - CSCL

Learning Speech Representation From Contrastive Token-Acoustic Pretraining. (arXiv:2309.00424v4 [eess.AS] UPDATED) 

arxiv.org/abs/2309.00424

0
arXiv - CSCL

DS4DH at #SMM4H 2023: Zero-Shot Adverse Drug Events Normalization using Sentence Transformers and Reciprocal-Rank Fusion. (arXiv:2308.12877v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.12877

0
arXiv - CSCL

Advancing Beyond Identification: Multi-bit Watermark for Large Language Models. (arXiv:2308.00221v2 [cs.CL] UPDATED) 

arxiv.org/abs/2308.00221

0
arXiv - CSCL

Robust Distortion-free Watermarks for Language Models. (arXiv:2307.15593v2 [cs.LG] UPDATED) 

arxiv.org/abs/2307.15593

0
arXiv - CSCL

Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features. (arXiv:2307.07683v2 [cs.SD] UPDATED) 

arxiv.org/abs/2307.07683

0
arXiv - CSCL

Beyond Scale: the Diversity Coefficient as a Data Quality Metric Demonstrates LLMs are Pre-trained on Formally Diverse Data. (arXiv:2306.13840v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.13840

0
arXiv - CSCL

AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers. (arXiv:2306.06531v2 [cs.RO] UPDATED) 

arxiv.org/abs/2306.06531

0
arXiv - CSCL

Large Language Models Can Be Used to Estimate the Latent Positions of Politicians. (arXiv:2303.12057v4 [cs.CY] UPDATED) 

arxiv.org/abs/2303.12057

0
arXiv - CSCL

A Deep Learning System for Domain-specific Speech Recognition. (arXiv:2303.10510v2 [cs.CL] UPDATED) 

arxiv.org/abs/2303.10510

0
arXiv - CSCL

GPT-Neo for commonsense reasoning -- a theoretical and practical lens. (arXiv:2211.15593v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.15593

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