Show newer
arXiv - CSCL

Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation. (arXiv:2311.00953v1 [cs.CL]) 

arxiv.org/abs/2311.00953

0
arXiv - CSCL

E3 TTS: Easy End-to-End Diffusion-based Text to Speech. (arXiv:2311.00945v1 [cs.SD]) 

arxiv.org/abs/2311.00945

0
arXiv - CSCL

Task-Agnostic Low-Rank Adapters for Unseen English Dialects. (arXiv:2311.00915v1 [cs.CL]) 

arxiv.org/abs/2311.00915

0
arXiv - CSCL

Self-Influence Guided Data Reweighting for Language Model Pre-training. (arXiv:2311.00913v1 [cs.CL]) 

arxiv.org/abs/2311.00913

0
arXiv - CSCL

Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition. (arXiv:2311.00906v1 [cs.CL]) 

arxiv.org/abs/2311.00906

0
arXiv - CSCL

On The Open Prompt Challenge In Conditional Audio Generation. (arXiv:2311.00897v1 [cs.SD]) 

arxiv.org/abs/2311.00897

0
arXiv - CSCL

In-Context Prompt Editing For Conditional Audio Generation. (arXiv:2311.00895v1 [cs.SD]) 

arxiv.org/abs/2311.00895

0
arXiv - CSCL

Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models. (arXiv:2311.00871v1 [cs.LG]) 

arxiv.org/abs/2311.00871

0
arXiv - CSCL

Automatic Disfluency Detection from Untranscribed Speech. (arXiv:2311.00867v1 [eess.AS]) 

arxiv.org/abs/2311.00867

0
arXiv - CSCL

Training Dynamics of Contextual N-Grams in Language Models. (arXiv:2311.00863v1 [cs.LG]) 

arxiv.org/abs/2311.00863

0
arXiv - CSCL

Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity Typing. (arXiv:2311.00835v1 [cs.CL]) 

arxiv.org/abs/2311.00835

0
arXiv - CSCL

Construction Artifacts in Metaphor Identification Datasets. (arXiv:2311.00790v1 [cs.CL]) 

arxiv.org/abs/2311.00790

0
arXiv - CSCL

Language Model Training Paradigms for Clinical Feature Embeddings. (arXiv:2311.00768v1 [cs.LG]) 

arxiv.org/abs/2311.00768

0
arXiv - CSCL

Challenges for Linguistically-Driven Computer-Based Sign Recognition from Continuous Signing for American Sign Language. (arXiv:2311.00762v1 [cs.CV]) 

arxiv.org/abs/2311.00762

0
arXiv - CSCL

Can Large Language Models Design Accurate Label Functions?. (arXiv:2311.00739v1 [cs.CL]) 

arxiv.org/abs/2311.00739

0
arXiv - CSCL

tmn at #SMM4H 2023: Comparing Text Preprocessing Techniques for Detecting Tweets Self-reporting a COVID-19 Diagnosis. (arXiv:2311.00732v1 [cs.CL]) 

arxiv.org/abs/2311.00732

0
arXiv - CSCL

JADE: A Linguistics-based Safety Evaluation Platform for LLM. (arXiv:2311.00286v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.00286

0
arXiv - CSCL

Meaning Representations from Trajectories in Autoregressive Models. (arXiv:2310.18348v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.18348

0
arXiv - CSCL

Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering. (arXiv:2310.17490v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.17490

0
arXiv - CSCL

Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation. (arXiv:2310.14892v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.14892

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