Show newer
arXiv - CSCL

Generative Dense Retrieval: Memory Can Be a Burden. (arXiv:2401.10487v1 [cs.IR]) 

arxiv.org/abs/2401.10487

0
arXiv - CSCL

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning. (arXiv:2401.10480v1 [cs.CL]) 

arxiv.org/abs/2401.10480

0
arXiv - CSCL

Name Tagging Under Domain Shift via Metric Learning for Life Sciences. (arXiv:2401.10472v1 [cs.CL]) 

arxiv.org/abs/2401.10472

0
arXiv - CSCL

DeepEdit: Knowledge Editing as Decoding with Constraints. (arXiv:2401.10471v1 [cs.CL]) 

arxiv.org/abs/2401.10471

0
arXiv - CSCL

Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech. (arXiv:2401.10465v1 [cs.CL]) 

arxiv.org/abs/2401.10465

0
arXiv - CSCL

Critical Data Size of Language Models from a Grokking Perspective. (arXiv:2401.10463v1 [cs.CL]) 

arxiv.org/abs/2401.10463

0
arXiv - CSCL

Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search. (arXiv:2401.10449v1 [eess.AS]) 

arxiv.org/abs/2401.10449

0
arXiv - CSCL

Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition. (arXiv:2401.10447v1 [cs.CL]) 

arxiv.org/abs/2401.10447

0
arXiv - CSCL

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition. (arXiv:2401.10446v1 [cs.CL]) 

arxiv.org/abs/2401.10446

0
arXiv - CSCL

Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models. (arXiv:2401.10440v1 [cs.CL]) 

arxiv.org/abs/2401.10440

0
arXiv - CSCL

Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?. (arXiv:2401.10415v1 [cs.CL]) 

arxiv.org/abs/2401.10415

0
arXiv - CSCL

Learning High-Quality and General-Purpose Phrase Representations. (arXiv:2401.10407v1 [cs.CL]) 

arxiv.org/abs/2401.10407

0
arXiv - CSCL

Inconsistent dialogue responses and how to recover from them. (arXiv:2401.10353v1 [cs.CL]) 

arxiv.org/abs/2401.10353

0
arXiv - CSCL

Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys. (arXiv:2401.10352v1 [cs.CL]) 

arxiv.org/abs/2401.10352

0
arXiv - CSCL

Noise Contrastive Estimation-based Matching Framework for Low-resource Security Attack Pattern Recognition. (arXiv:2401.10337v1 [cs.LG]) 

arxiv.org/abs/2401.10337

0
arXiv - CSCL

DrugAssist: A Large Language Model for Molecule Optimization. (arXiv:2401.10334v1 [q-bio.QM]) 

arxiv.org/abs/2401.10334

0
arXiv - CSCL

Top in Chinese Data Processing: English Code Models. (arXiv:2401.10286v1 [cs.CL]) 

arxiv.org/abs/2401.10286

0
arXiv - CSCL

A systematic review of geospatial location embedding approaches in large language models: A path to spatial AI systems. (arXiv:2401.10279v1 [cs.IR]) 

arxiv.org/abs/2401.10279

0
arXiv - CSCL

Knowledge graph driven recommendation model of graph neural network. (arXiv:2401.10244v1 [cs.IR]) 

arxiv.org/abs/2401.10244

0
arXiv - CSCL

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation. (arXiv:2401.08417v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.08417

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