Show newer
arXiv - CSCL

Language Generation from Human Brain Activities. (arXiv:2311.09889v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.09889

0
arXiv - CSCL

A Survey on Language Models for Code. (arXiv:2311.07989v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07989

0
arXiv - CSCL

In-context Learning and Gradient Descent Revisited. (arXiv:2311.07772v3 [cs.CL] UPDATED) 

arxiv.org/abs/2311.07772

0
arXiv - CSCL

Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains. (arXiv:2311.07723v2 [cs.AI] UPDATED) 

arxiv.org/abs/2311.07723

0
arXiv - CSCL

DocGen: Generating Detailed Parameter Docstrings in Python. (arXiv:2311.06453v3 [cs.SE] UPDATED) 

arxiv.org/abs/2311.06453

0
arXiv - CSCL

Pre-training LLMs using human-like development data corpus. (arXiv:2311.04666v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.04666

0
arXiv - CSCL

Generating Medical Prescriptions with Conditional Transformer. (arXiv:2310.19727v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.19727

0
arXiv - CSCL

Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender. (arXiv:2310.19130v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.19130

0
arXiv - CSCL

Using GPT-4 to Augment Unbalanced Data for Automatic Scoring. (arXiv:2310.18365v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.18365

0
arXiv - CSCL

SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations. (arXiv:2310.16676v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.16676

0
arXiv - CSCL

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models. (arXiv:2310.15127v2 [cs.AI] UPDATED) 

arxiv.org/abs/2310.15127

0
arXiv - CSCL

Is ChatGPT a game changer for geocoding - a benchmark for geocoding address parsing techniques. (arXiv:2310.14360v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.14360

0
arXiv - CSCL

Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting. (arXiv:2310.11732v2 [cs.LG] UPDATED) 

arxiv.org/abs/2310.11732

0
arXiv - CSCL

Attribution Patching Outperforms Automated Circuit Discovery. (arXiv:2310.10348v2 [cs.LG] UPDATED) 

arxiv.org/abs/2310.10348

0
arXiv - CSCL

Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation. (arXiv:2310.09886v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.09886

0
arXiv - CSCL

Solving Math Word Problems with Reexamination. (arXiv:2310.09590v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.09590

0
arXiv - CSCL

From Large Language Models to Knowledge Graphs for Biomarker Discovery in Cancer. (arXiv:2310.08365v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.08365

0
arXiv - CSCL

A novel approach to measuring patent claim scope based on probabilities obtained from (large) language models. (arXiv:2309.10003v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.10003

0
arXiv - CSCL

Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP. (arXiv:2309.05619v2 [cs.CL] UPDATED) 

arxiv.org/abs/2309.05619

0
arXiv - CSCL

Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation. (arXiv:2308.15363v4 [cs.DB] UPDATED) 

arxiv.org/abs/2308.15363

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