Show newer
arXiv - CSCL

Improved Beam Search for Hallucination Mitigation in Abstractive Summarization. (arXiv:2212.02712v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.02712

0
arXiv - CSCL

Simplifying and Understanding State Space Models with Diagonal Linear RNNs. (arXiv:2212.00768v3 [cs.LG] UPDATED) 

arxiv.org/abs/2212.00768

0
arXiv - CSCL

ComCLIP: Training-Free Compositional Image and Text Matching. (arXiv:2211.13854v3 [cs.CV] UPDATED) 

arxiv.org/abs/2211.13854

0
arXiv - CSCL

CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals. (arXiv:2106.05544v3 [cs.CL] UPDATED) 

arxiv.org/abs/2106.05544

0
arXiv - CSCL

Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks. (arXiv:2311.08273v1 [cs.CL]) 

arxiv.org/abs/2311.08273

0
arXiv - CSCL

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily. (arXiv:2311.08268v1 [cs.CL]) 

arxiv.org/abs/2311.08268

0
arXiv - CSCL

Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster. (arXiv:2311.08263v1 [cs.CL]) 

arxiv.org/abs/2311.08263

0
arXiv - CSCL

REST: Retrieval-Based Speculative Decoding. (arXiv:2311.08252v1 [cs.CL]) 

arxiv.org/abs/2311.08252

0
arXiv - CSCL

On Using Distribution-Based Compositionality Assessment to Evaluate Compositional Generalisation in Machine Translation. (arXiv:2311.08249v1 [cs.CL]) 

arxiv.org/abs/2311.08249

0
arXiv - CSCL

Investigating the Encoding of Words in BERT's Neurons using Feature Textualization. (arXiv:2311.08240v1 [cs.CL]) 

arxiv.org/abs/2311.08240

0
arXiv - CSCL

Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction. (arXiv:2311.08219v1 [cs.CL]) 

arxiv.org/abs/2311.08219

0
arXiv - CSCL

Unlock the Power: Competitive Distillation for Multi-Modal Large Language Models. (arXiv:2311.08213v1 [cs.CV]) 

arxiv.org/abs/2311.08213

0
arXiv - CSCL

Human-Centric Autonomous Systems With LLMs for User Command Reasoning. (arXiv:2311.08206v1 [cs.CL]) 

arxiv.org/abs/2311.08206

0
arXiv - CSCL

Automated Fact-Checking in Dialogue: Are Specialized Models Needed?. (arXiv:2311.08195v1 [cs.CL]) 

arxiv.org/abs/2311.08195

0
arXiv - CSCL

GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding. (arXiv:2311.08191v1 [cs.CL]) 

arxiv.org/abs/2311.08191

0
arXiv - CSCL

Unlocking Science: Novel Dataset and Benchmark for Cross-Modality Scientific Information Extraction. (arXiv:2311.08189v1 [cs.CL]) 

arxiv.org/abs/2311.08189

0
arXiv - CSCL

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning. (arXiv:2311.08182v1 [cs.CL]) 

arxiv.org/abs/2311.08182

0
arXiv - CSCL

MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge. (arXiv:2311.08166v1 [cs.AI]) 

arxiv.org/abs/2311.08166

0
arXiv - CSCL

Ask One More Time: Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios. (arXiv:2311.08154v1 [cs.CL]) 

arxiv.org/abs/2311.08154

0
arXiv - CSCL

Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration. (arXiv:2311.08152v1 [cs.CL]) 

arxiv.org/abs/2311.08152

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