Show newer
arXiv - CSCL

Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory. (arXiv:2311.08719v1 [cs.CL]) 

arxiv.org/abs/2311.08719

0
arXiv - CSCL

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling. (arXiv:2311.08718v1 [cs.CL]) 

arxiv.org/abs/2311.08718

0
arXiv - CSCL

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning. (arXiv:2311.08711v1 [cs.CL]) 

arxiv.org/abs/2311.08711

0
arXiv - CSCL

Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations. (arXiv:2311.08705v1 [cs.CL]) 

arxiv.org/abs/2311.08705

0
arXiv - CSCL

Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains. (arXiv:2311.08704v1 [cs.CL]) 

arxiv.org/abs/2311.08704

0
arXiv - CSCL

Debate Helps Supervise Unreliable Experts. (arXiv:2311.08702v1 [cs.AI]) 

arxiv.org/abs/2311.08702

0
arXiv - CSCL

Attribute Diversity Determines the Systematicity Gap in VQA. (arXiv:2311.08695v1 [cs.LG]) 

arxiv.org/abs/2311.08695

0
arXiv - CSCL

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models. (arXiv:2311.08692v1 [cs.CL]) 

arxiv.org/abs/2311.08692

0
arXiv - CSCL

An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping. (arXiv:2311.08687v1 [cs.CL]) 

arxiv.org/abs/2311.08687

0
arXiv - CSCL

Safer-Instruct: Aligning Language Models with Automated Preference Data. (arXiv:2311.08685v1 [cs.CL]) 

arxiv.org/abs/2311.08685

0
arXiv - CSCL

Understanding Calibration for Multilingual Question Answering Models. (arXiv:2311.08669v1 [cs.CL]) 

arxiv.org/abs/2311.08669

0
arXiv - CSCL

It Takes Two to Negotiate: Modeling Social Exchange in Online Multiplayer Games. (arXiv:2311.08666v1 [cs.CL]) 

arxiv.org/abs/2311.08666

0
arXiv - CSCL

Multi-Set Inoculation: Assessing Model Robustness Across Multiple Challenge Sets. (arXiv:2311.08662v1 [cs.CL]) 

arxiv.org/abs/2311.08662

0
arXiv - CSCL

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification. (arXiv:2311.08648v1 [cs.CL]) 

arxiv.org/abs/2311.08648

0
arXiv - CSCL

Multistage Collaborative Knowledge Distillation from Large Language Models. (arXiv:2311.08640v1 [cs.CL]) 

arxiv.org/abs/2311.08640

0
arXiv - CSCL

Formal Proofs as Structured Explanations: Proposing Several Tasks on Explainable Natural Language Inference. (arXiv:2311.08637v1 [cs.CL]) 

arxiv.org/abs/2311.08637

0
arXiv - CSCL

DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models. (arXiv:2311.08623v1 [cs.CV]) 

arxiv.org/abs/2311.08623

0
arXiv - CSCL

Multiple-Question Multiple-Answer Text-VQA. (arXiv:2311.08622v1 [cs.CV]) 

arxiv.org/abs/2311.08622

0
arXiv - CSCL

Toucan: Token-Aware Character Level Language Modeling. (arXiv:2311.08620v1 [cs.CL]) 

arxiv.org/abs/2311.08620

0
arXiv - CSCL

XplainLLM: A QA Explanation Dataset for Understanding LLM Decision-Making. (arXiv:2311.08614v1 [cs.CL]) 

arxiv.org/abs/2311.08614

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