Show newer
arXiv - CSCL

Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models. (arXiv:2311.01732v1 [cs.CL]) 

arxiv.org/abs/2311.01732

0
arXiv - CSCL

An Empirical Study of Benchmarking Chinese Aspect Sentiment Quad Prediction. (arXiv:2311.01713v1 [cs.CL]) 

arxiv.org/abs/2311.01713

0
arXiv - CSCL

A New Korean Text Classification Benchmark for Recognizing the Political Intents in Online Newspapers. (arXiv:2311.01712v1 [cs.CL]) 

arxiv.org/abs/2311.01712

0
arXiv - CSCL

Data-Free Distillation of Language Model by Text-to-Text Transfer. (arXiv:2311.01689v1 [cs.CL]) 

arxiv.org/abs/2311.01689

0
arXiv - CSCL

CASE: Commonsense-Augmented Score with an Expanded Answer Space. (arXiv:2311.01684v1 [cs.CL]) 

arxiv.org/abs/2311.01684

0
arXiv - CSCL

DialogBench: Evaluating LLMs as Human-like Dialogue Systems. (arXiv:2311.01677v1 [cs.CL]) 

arxiv.org/abs/2311.01677

0
arXiv - CSCL

Plot Retrieval as an Assessment of Abstract Semantic Association. (arXiv:2311.01666v1 [cs.IR]) 

arxiv.org/abs/2311.01666

0
arXiv - CSCL

MARRS: Multimodal Reference Resolution System. (arXiv:2311.01650v1 [cs.CL]) 

arxiv.org/abs/2311.01650

0
arXiv - CSCL

VQPy: An Object-Oriented Approach to Modern Video Analytics. (arXiv:2311.01623v1 [cs.CV]) 

arxiv.org/abs/2311.01623

0
arXiv - CSCL

ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos. (arXiv:2311.01620v1 [cs.CV]) 

arxiv.org/abs/2311.01620

0
arXiv - CSCL

FLAP: Fast Language-Audio Pre-training. (arXiv:2311.01615v1 [cs.SD]) 

arxiv.org/abs/2311.01615

0
arXiv - CSCL

KG-FRUS: a Novel Graph-based Dataset of 127 Years of US Diplomatic Relations. (arXiv:2311.01606v1 [cs.CL]) 

arxiv.org/abs/2311.01606

0
arXiv - CSCL

Faithful and Robust Local Interpretability for Textual Predictions. (arXiv:2311.01605v1 [cs.CL]) 

arxiv.org/abs/2311.01605

0
arXiv - CSCL

MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition. (arXiv:2311.01580v1 [cs.CL]) 

arxiv.org/abs/2311.01580

0
arXiv - CSCL

Preserving the knowledge of long clinical texts using aggregated ensembles of large language models. (arXiv:2311.01571v1 [cs.CL]) 

arxiv.org/abs/2311.01571

0
arXiv - CSCL

Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers. (arXiv:2311.01555v1 [cs.IR]) 

arxiv.org/abs/2311.01555

0
arXiv - CSCL

Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization. (arXiv:2311.01544v1 [cs.CL]) 

arxiv.org/abs/2311.01544

0
arXiv - CSCL

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning. (arXiv:2311.01487v1 [cs.CV]) 

arxiv.org/abs/2311.01487

0
arXiv - CSCL

Relation Extraction from News Articles (RENA): A Tool for Epidemic Surveillance. (arXiv:2311.01472v1 [cs.CL]) 

arxiv.org/abs/2311.01472

0
arXiv - CSCL

Leveraging Language Models to Detect Greenwashing. (arXiv:2311.01469v1 [cs.CL]) 

arxiv.org/abs/2311.01469

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