Show newer
arXiv - CSCL

Don't throw away your value model! Making PPO even better via Value-Guided Monte-Carlo Tree Search decoding. (arXiv:2309.15028v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.15028

0
arXiv - CSCL

Foundation Metrics: Quantifying Effectiveness of Healthcare Conversations powered by Generative AI. (arXiv:2309.12444v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.12444

0
arXiv - CSCL

Comparative Performance Evaluation of Large Language Models for Extracting Molecular Interactions and Pathway Knowledge. (arXiv:2307.08813v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.08813

0
arXiv - CSCL

Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition. (arXiv:2307.07280v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.07280

0
arXiv - CSCL

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias. (arXiv:2306.15895v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.15895

0
arXiv - CSCL

PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts. (arXiv:2306.04528v4 [cs.CL] UPDATED) 

arxiv.org/abs/2306.04528

0
arXiv - CSCL

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey. (arXiv:2305.18703v6 [cs.CL] UPDATED) 

arxiv.org/abs/2305.18703

0
arXiv - CSCL

Difference-Masking: Choosing What to Mask in Continued Pretraining. (arXiv:2305.14577v2 [cs.LG] UPDATED) 

arxiv.org/abs/2305.14577

0
arXiv - CSCL

Question Answering as Programming for Solving Time-Sensitive Questions. (arXiv:2305.14221v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14221

0
arXiv - CSCL

When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale. (arXiv:2305.14124v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14124

0
arXiv - CSCL

MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation. (arXiv:2305.12733v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12733

0
arXiv - CSCL

Multilingual Simplification of Medical Texts. (arXiv:2305.12532v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12532

0
arXiv - CSCL

Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge. (arXiv:2305.12212v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12212

0
arXiv - CSCL

Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization. (arXiv:2305.12169v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12169

0
arXiv - CSCL

Revisiting Entropy Rate Constancy in Text. (arXiv:2305.12084v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12084

0
arXiv - CSCL

Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews. (arXiv:2305.11828v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11828

0
arXiv - CSCL

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate. (arXiv:2305.11595v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11595

0
arXiv - CSCL

PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning. (arXiv:2305.11508v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11508

0
arXiv - CSCL

Cross-modality Data Augmentation for End-to-End Sign Language Translation. (arXiv:2305.11096v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.11096

0
arXiv - CSCL

Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks. (arXiv:2305.10160v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.10160

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