Show newer
arXiv - CSCL

GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition. (arXiv:2306.07848v8 [cs.CL] UPDATED) 

arxiv.org/abs/2306.07848

0
arXiv - CSCL

Do Language Models Know When They're Hallucinating References?. (arXiv:2305.18248v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18248

0
arXiv - CSCL

Does ChatGPT have Theory of Mind?. (arXiv:2305.14020v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14020

0
arXiv - CSCL

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model. (arXiv:2305.06908v2 [cs.SD] UPDATED) 

arxiv.org/abs/2305.06908

0
arXiv - CSCL

Processing Natural Language on Embedded Devices: How Well Do Modern Models Perform?. (arXiv:2304.11520v3 [cs.CL] UPDATED) 

arxiv.org/abs/2304.11520

0
arXiv - CSCL

Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects. (arXiv:2304.11075v2 [cs.CL] UPDATED) 

arxiv.org/abs/2304.11075

0
arXiv - CSCL

Diminished Diversity-of-Thought in a Standard Large Language Model. (arXiv:2302.07267v6 [cs.HC] UPDATED) 

arxiv.org/abs/2302.07267

0
arXiv - CSCL

ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning. (arXiv:2212.01378v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.01378

0
arXiv - CSCL

Event and Entity Extraction from Generated Video Captions. (arXiv:2211.02982v3 [cs.CV] UPDATED) 

arxiv.org/abs/2211.02982

0
arXiv - CSCL

RAIN: Your Language Models Can Align Themselves without Finetuning. (arXiv:2309.07124v1 [cs.CL]) 

arxiv.org/abs/2309.07124

0
arXiv - CSCL

Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics. (arXiv:2309.07120v1 [cs.CL]) 

arxiv.org/abs/2309.07120

0
arXiv - CSCL

Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding. (arXiv:2309.07098v1 [cs.CL]) 

arxiv.org/abs/2309.07098

0
arXiv - CSCL

Can Whisper perform speech-based in-context learning. (arXiv:2309.07081v1 [eess.AS]) 

arxiv.org/abs/2309.07081

0
arXiv - CSCL

Large Language Models for Compiler Optimization. (arXiv:2309.07062v1 [cs.PL]) 

arxiv.org/abs/2309.07062

0
arXiv - CSCL

SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions. (arXiv:2309.07045v1 [cs.CL]) 

arxiv.org/abs/2309.07045

0
arXiv - CSCL

How (Not) to Use Sociodemographic Information for Subjective NLP Tasks. (arXiv:2309.07034v1 [cs.CL]) 

arxiv.org/abs/2309.07034

0
arXiv - CSCL

Beyond original Research Articles Categorization via NLP. (arXiv:2309.07020v1 [cs.CL]) 

arxiv.org/abs/2309.07020

0
arXiv - CSCL

R\'esum\'e Parsing as Hierarchical Sequence Labeling: An Empirical Study. (arXiv:2309.07015v1 [cs.CL]) 

arxiv.org/abs/2309.07015

0
arXiv - CSCL

OYXOY: A Modern NLP Test Suite for Modern Greek. (arXiv:2309.07009v1 [cs.CL]) 

arxiv.org/abs/2309.07009

0
arXiv - CSCL

Unsupervised Contrast-Consistent Ranking with Language Models. (arXiv:2309.06991v1 [cs.LG]) 

arxiv.org/abs/2309.06991

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