Show newer
arXiv - CSCL

AMRFact: Enhancing Summarization Factuality Evaluation with AMR-driven Training Data Generation. (arXiv:2311.09521v1 [cs.CL]) 

arxiv.org/abs/2311.09521

0
arXiv - CSCL

Leveraging Code to Improve In-context Learning for Semantic Parsing. (arXiv:2311.09519v1 [cs.CL]) 

arxiv.org/abs/2311.09519

0
arXiv - CSCL

GEE! Grammar Error Explanation with Large Language Models. (arXiv:2311.09517v1 [cs.CL]) 

arxiv.org/abs/2311.09517

0
arXiv - CSCL

Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents. (arXiv:2311.09513v1 [cs.CL]) 

arxiv.org/abs/2311.09513

0
arXiv - CSCL

One Size Does Not Fit All: Customizing Open-Domain Procedures. (arXiv:2311.09510v1 [cs.CL]) 

arxiv.org/abs/2311.09510

0
arXiv - CSCL

SegMix: A Simple Structure-Aware Data Augmentation Method. (arXiv:2311.09505v1 [cs.CL]) 

arxiv.org/abs/2311.09505

0
arXiv - CSCL

SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU. (arXiv:2311.09502v1 [cs.CL]) 

arxiv.org/abs/2311.09502

0
arXiv - CSCL

Personalized Jargon Identification for Enhanced Interdisciplinary Communication. (arXiv:2311.09481v1 [cs.CL]) 

arxiv.org/abs/2311.09481

0
arXiv - CSCL

Show Your Work with Confidence: Confidence Bands for Tuning Curves. (arXiv:2311.09480v1 [cs.CL]) 

arxiv.org/abs/2311.09480

0
arXiv - CSCL

ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems. (arXiv:2311.09476v1 [cs.CL]) 

arxiv.org/abs/2311.09476

0
arXiv - CSCL

JAB: Joint Adversarial Prompting and Belief Augmentation. (arXiv:2311.09473v1 [cs.AI]) 

arxiv.org/abs/2311.09473

0
arXiv - CSCL

Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs. (arXiv:2311.09469v1 [cs.CL]) 

arxiv.org/abs/2311.09469

0
arXiv - CSCL

Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation. (arXiv:2311.09467v1 [cs.CL]) 

arxiv.org/abs/2311.09467

0
arXiv - CSCL

Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries. (arXiv:2311.09458v1 [cs.CL]) 

arxiv.org/abs/2311.09458

0
arXiv - CSCL

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities. (arXiv:2311.09447v1 [cs.CL]) 

arxiv.org/abs/2311.09447

0
arXiv - CSCL

Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset. (arXiv:2311.09443v1 [cs.CL]) 

arxiv.org/abs/2311.09443

0
arXiv - CSCL

Labeled Interactive Topic Models. (arXiv:2311.09438v1 [cs.LG]) 

arxiv.org/abs/2311.09438

0
arXiv - CSCL

Backdoor Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment. (arXiv:2311.09433v1 [cs.CR]) 

arxiv.org/abs/2311.09433

0
arXiv - CSCL

Striped Attention: Faster Ring Attention for Causal Transformers. (arXiv:2311.09431v1 [cs.LG]) 

arxiv.org/abs/2311.09431

0
arXiv - CSCL

Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models. (arXiv:2311.09428v1 [cs.CL]) 

arxiv.org/abs/2311.09428

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