Show newer
arXiv - CSCL

Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty. (arXiv:2401.06730v1 [cs.CL]) 

arxiv.org/abs/2401.06730

0
arXiv - CSCL

Reframing Tax Law Entailment as Analogical Reasoning. (arXiv:2401.06715v1 [cs.CL]) 

arxiv.org/abs/2401.06715

0
arXiv - CSCL

Few-Shot Detection of Machine-Generated Text using Style Representations. (arXiv:2401.06712v1 [cs.CL]) 

arxiv.org/abs/2401.06712

0
arXiv - CSCL

Reliability Analysis of Psychological Concept Extraction and Classification in User-penned Text. (arXiv:2401.06709v1 [cs.CL]) 

arxiv.org/abs/2401.06709

0
arXiv - CSCL

Multi-Candidate Speculative Decoding. (arXiv:2401.06706v1 [cs.CL]) 

arxiv.org/abs/2401.06706

0
arXiv - CSCL

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models. (arXiv:2401.06692v1 [cs.CL]) 

arxiv.org/abs/2401.06692

0
arXiv - CSCL

Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation. (arXiv:2401.06688v1 [cs.CL]) 

arxiv.org/abs/2401.06688

0
arXiv - CSCL

Proximal Causal Inference With Text Data. (arXiv:2401.06687v1 [cs.CL]) 

arxiv.org/abs/2401.06687

0
arXiv - CSCL

DQNC2S: DQN-based Cross-stream Crisis event Summarizer. (arXiv:2401.06683v1 [cs.IR]) 

arxiv.org/abs/2401.06683

0
arXiv - CSCL

PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler. (arXiv:2401.06665v1 [cs.DC]) 

arxiv.org/abs/2401.06665

0
arXiv - CSCL

WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge. (arXiv:2401.06659v1 [cs.CL]) 

arxiv.org/abs/2401.06659

0
arXiv - CSCL

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. (arXiv:2401.06643v1 [cs.CL]) 

arxiv.org/abs/2401.06643

0
arXiv - CSCL

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently. (arXiv:2401.06640v1 [cs.CL]) 

arxiv.org/abs/2401.06640

0
arXiv - CSCL

OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models. (arXiv:2401.06628v1 [cs.CL]) 

arxiv.org/abs/2401.06628

0
arXiv - CSCL

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models. (arXiv:2401.06620v1 [cs.CL]) 

arxiv.org/abs/2401.06620

0
arXiv - CSCL

Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Case Study. (arXiv:2401.06603v1 [cs.CL]) 

arxiv.org/abs/2401.06603

0
arXiv - CSCL

Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation. (arXiv:2401.06591v1 [cs.CL]) 

arxiv.org/abs/2401.06591

0
arXiv - CSCL

Mapping Transformer Leveraged Embeddings for Cross-Lingual Document Representation. (arXiv:2401.06583v1 [cs.CL]) 

arxiv.org/abs/2401.06583

0
arXiv - CSCL

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation. (arXiv:2401.06568v1 [cs.CL]) 

arxiv.org/abs/2401.06568

0
arXiv - CSCL

Intention Analysis Prompting Makes Large Language Models A Good Jailbreak Defender. (arXiv:2401.06561v1 [cs.CL]) 

arxiv.org/abs/2401.06561

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