Show newer
arXiv - CSCL

Secrets of RLHF in Large Language Models Part I: PPO. (arXiv:2307.04964v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.04964

0
arXiv - CSCL

A Survey on Evaluation of Large Language Models. (arXiv:2307.03109v5 [cs.CL] UPDATED) 

arxiv.org/abs/2307.03109

0
arXiv - CSCL

Enhancing LLM with Evolutionary Fine Tuning for News Summary Generation. (arXiv:2307.02839v2 [cs.CL] UPDATED) 

arxiv.org/abs/2307.02839

0
arXiv - CSCL

Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese. (arXiv:2306.15788v2 [cs.CL] UPDATED) 

arxiv.org/abs/2306.15788

0
arXiv - CSCL

SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design. (arXiv:2306.15656v3 [cs.LG] UPDATED) 

arxiv.org/abs/2306.15656

0
arXiv - CSCL

Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs. (arXiv:2305.14279v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.14279

0
arXiv - CSCL

Evaluating Open-QA Evaluation. (arXiv:2305.12421v2 [cs.CL] UPDATED) 

arxiv.org/abs/2305.12421

0
arXiv - CSCL

GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding. (arXiv:2305.09360v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.09360

0
arXiv - CSCL

Jointly Extracting Interventions, Outcomes, and Findings from RCT Reports with LLMs. (arXiv:2305.03642v3 [cs.CL] UPDATED) 

arxiv.org/abs/2305.03642

0
arXiv - CSCL

Persian topic detection based on Human Word association and graph embedding. (arXiv:2302.09775v2 [cs.CL] UPDATED) 

arxiv.org/abs/2302.09775

0
arXiv - CSCL

Execution-based Code Generation using Deep Reinforcement Learning. (arXiv:2301.13816v3 [cs.LG] UPDATED) 

arxiv.org/abs/2301.13816

0
arXiv - CSCL

A Human Word Association based model for topic detection in social networks. (arXiv:2301.13066v2 [cs.CL] UPDATED) 

arxiv.org/abs/2301.13066

0
arXiv - CSCL

Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe. (arXiv:2210.14348v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.14348

0
arXiv - CSCL

InitialGAN: A Language GAN with Completely Random Initialization. (arXiv:2208.02531v3 [cs.CL] UPDATED) 

arxiv.org/abs/2208.02531

0
arXiv - CSCL

On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach. (arXiv:2104.06474v2 [cs.CL] UPDATED) 

arxiv.org/abs/2104.06474

0
arXiv - CSCL

Overthinking the Truth: Understanding how Language Models Process False Demonstrations. (arXiv:2307.09476v1 [cs.LG]) 

arxiv.org/abs/2307.09476

0
arXiv - CSCL

ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning. (arXiv:2307.09474v1 [cs.CL]) 

arxiv.org/abs/2307.09474

0
arXiv - CSCL

A comparative analysis of SR-GAN models. (arXiv:2307.09456v1 [cs.CV]) 

arxiv.org/abs/2307.09456

0
arXiv - CSCL

Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers. (arXiv:2307.09455v1 [cs.CL]) 

arxiv.org/abs/2307.09455

0
arXiv - CSCL

Let's ViCE! Mimicking Human Cognitive Behavior in Image Generation Evaluation. (arXiv:2307.09416v1 [cs.CV]) 

arxiv.org/abs/2307.09416

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