Show newer
arXiv - CSCL

Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation. (arXiv:2311.00684v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.00684

0
arXiv - CSCL

Machine Translation for Nko: Tools, Corpora and Baseline Results. (arXiv:2310.15612v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.15612

0
arXiv - CSCL

MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation. (arXiv:2310.14088v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.14088

0
arXiv - CSCL

AutoMix: Automatically Mixing Language Models. (arXiv:2310.12963v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12963

0
arXiv - CSCL

Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking. (arXiv:2310.12342v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.12342

0
arXiv - CSCL

VIBE: Topic-Driven Temporal Adaptation for Twitter Classification. (arXiv:2310.10191v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.10191

0
arXiv - CSCL

Fine-grained Conversational Decoding via Isotropic and Proximal Search. (arXiv:2310.08130v4 [cs.CL] UPDATED) 

arxiv.org/abs/2310.08130

0
arXiv - CSCL

Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model. (arXiv:2310.02971v3 [eess.AS] UPDATED) 

arxiv.org/abs/2310.02971

0
arXiv - CSCL

The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models. (arXiv:2310.02457v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.02457

0
arXiv - CSCL

When Do Program-of-Thoughts Work for Reasoning?. (arXiv:2308.15452v4 [cs.CL] UPDATED) 

arxiv.org/abs/2308.15452

0
arXiv - CSCL

ASPIRE: Language-Guided Augmentation for Robust Image Classification. (arXiv:2308.10103v2 [cs.CV] UPDATED) 

arxiv.org/abs/2308.10103

0
arXiv - CSCL

The Bias Amplification Paradox in Text-to-Image Generation. (arXiv:2308.00755v2 [cs.LG] UPDATED) 

arxiv.org/abs/2308.00755

0
arXiv - CSCL

CPET: Effective Parameter-Efficient Tuning for Compressed Large Language Models. (arXiv:2307.07705v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.07705

0
arXiv - CSCL

Citation: A Key to Building Responsible and Accountable Large Language Models. (arXiv:2307.02185v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.02185

0
arXiv - CSCL

$FastDoc$: Domain-Specific Fast Pre-training Technique using Document-Level Metadata and Taxonomy. (arXiv:2306.06190v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.06190

0
arXiv - CSCL

MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models. (arXiv:2305.19011v3 [eess.AS] UPDATED) 

arxiv.org/abs/2305.19011

0
arXiv - CSCL

Detecting Multidimensional Political Incivility on Social Media. (arXiv:2305.14964v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14964

0
arXiv - CSCL

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response. (arXiv:2305.14658v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14658

0
arXiv - CSCL

Selectively Answering Ambiguous Questions. (arXiv:2305.14613v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14613

0
arXiv - CSCL

Do prompt positions really matter?. (arXiv:2305.14493v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14493

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