Show newer
arXiv - CSCL

An Investigation of LLMs' Inefficacy in Understanding Converse Relations. (arXiv:2310.05163v3 [cs.CL] UPDATED) 

arxiv.org/abs/2310.05163

0
arXiv - CSCL

FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets. (arXiv:2310.04793v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.04793

0
arXiv - CSCL

KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services. (arXiv:2310.04313v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.04313

0
arXiv - CSCL

Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference. (arXiv:2310.03184v2 [cs.CL] UPDATED) 

arxiv.org/abs/2310.03184

0
arXiv - CSCL

Insights Into the Nutritional Prevention of Macular Degeneration based on a Comparative Topic Modeling Approach. (arXiv:2309.00312v3 [cs.CL] UPDATED) 

arxiv.org/abs/2309.00312

0
arXiv - CSCL

Activation Addition: Steering Language Models Without Optimization. (arXiv:2308.10248v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.10248

0
arXiv - CSCL

Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic. (arXiv:2308.07336v2 [cs.AI] UPDATED) 

arxiv.org/abs/2308.07336

0
arXiv - CSCL

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models. (arXiv:2308.06744v3 [cs.CL] UPDATED) 

arxiv.org/abs/2308.06744

0
arXiv - CSCL

Data Augmentation for Neural Machine Translation using Generative Language Model. (arXiv:2307.16833v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.16833

0
arXiv - CSCL

The Imitation Game: Detecting Human and AI-Generated Texts in the Era of ChatGPT and BARD. (arXiv:2307.12166v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.12166

0
arXiv - CSCL

AutoAlign: Fully Automatic and Effective Knowledge Graph Alignment enabled by Large Language Models. (arXiv:2307.11772v3 [cs.IR] UPDATED) 

arxiv.org/abs/2307.11772

0
arXiv - CSCL

Large Language Models Understand and Can be Enhanced by Emotional Stimuli. (arXiv:2307.11760v7 [cs.CL] UPDATED) 

arxiv.org/abs/2307.11760

0
arXiv - CSCL

An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing. (arXiv:2307.11254v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.11254

0
arXiv - CSCL

No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models. (arXiv:2307.06440v3 [cs.LG] UPDATED) 

arxiv.org/abs/2307.06440

0
arXiv - CSCL

RLTF: Reinforcement Learning from Unit Test Feedback. (arXiv:2307.04349v2 [cs.AI] UPDATED) 

arxiv.org/abs/2307.04349

0
arXiv - CSCL

Style Over Substance: Evaluation Biases for Large Language Models. (arXiv:2307.03025v3 [cs.CL] UPDATED) 

arxiv.org/abs/2307.03025

0
arXiv - CSCL

Learning to Generate Better Than Your LLM. (arXiv:2306.11816v2 [cs.LG] UPDATED) 

arxiv.org/abs/2306.11816

0
arXiv - CSCL

Source Code Data Augmentation for Deep Learning: A Survey. (arXiv:2305.19915v4 [cs.CL] UPDATED) 

arxiv.org/abs/2305.19915

0
arXiv - CSCL

Ghostbuster: Detecting Text Ghostwritten by Large Language Models. (arXiv:2305.15047v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.15047

0
arXiv - CSCL

Evaluation of African American Language Bias in Natural Language Generation. (arXiv:2305.14291v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14291

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