Show newer
arXiv - CSCL

Aligning Large Language Models with Counterfactual DPO. (arXiv:2401.09566v1 [cs.CL]) 

arxiv.org/abs/2401.09566

0
arXiv - CSCL

Improving Classification Performance With Human Feedback: Label a few, we label the rest. (arXiv:2401.09555v1 [cs.LG]) 

arxiv.org/abs/2401.09555

0
arXiv - CSCL

BERTologyNavigator: Advanced Question Answering with BERT-based Semantics. (arXiv:2401.09553v1 [cs.CL]) 

arxiv.org/abs/2401.09553

0
arXiv - CSCL

LoMA: Lossless Compressed Memory Attention. (arXiv:2401.09486v1 [cs.LG]) 

arxiv.org/abs/2401.09486

0
arXiv - CSCL

Voila-A: Aligning Vision-Language Models with User's Gaze Attention. (arXiv:2401.09454v1 [cs.CV]) 

arxiv.org/abs/2401.09454

0
arXiv - CSCL

Explainable Multimodal Sentiment Analysis on Bengali Memes. (arXiv:2401.09446v1 [cs.CV]) 

arxiv.org/abs/2401.09446

0
arXiv - CSCL

RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models. (arXiv:2401.09432v1 [cs.CL]) 

arxiv.org/abs/2401.09432

0
arXiv - CSCL

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models. (arXiv:2401.06102v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.06102

0
arXiv - CSCL

LEGO:Language Enhanced Multi-modal Grounding Model. (arXiv:2401.06071v2 [cs.CV] UPDATED) 

arxiv.org/abs/2401.06071

0
arXiv - CSCL

Universal Vulnerabilities in Large Language Models: In-context Learning Backdoor Attacks. (arXiv:2401.05949v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.05949

0
arXiv - CSCL

Generative Deduplication For Socia Media Data Selection. (arXiv:2401.05883v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.05883

0
arXiv - CSCL

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training. (arXiv:2401.05566v2 [cs.CR] UPDATED) 

arxiv.org/abs/2401.05566

0
arXiv - CSCL

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation. (arXiv:2401.04679v4 [cs.CL] UPDATED) 

arxiv.org/abs/2401.04679

0
arXiv - CSCL

MERA: A Comprehensive LLM Evaluation in Russian. (arXiv:2401.04531v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.04531

0
arXiv - CSCL

Can AI Be as Creative as Humans?. (arXiv:2401.01623v3 [cs.AI] UPDATED) 

arxiv.org/abs/2401.01623

0
arXiv - CSCL

LLaMA Beyond English: An Empirical Study on Language Capability Transfer. (arXiv:2401.01055v2 [cs.CL] UPDATED) 

arxiv.org/abs/2401.01055

0
arXiv - CSCL

Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition. (arXiv:2312.17279v2 [cs.CL] UPDATED) 

arxiv.org/abs/2312.17279

0
arXiv - CSCL

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes. (arXiv:2312.14890v3 [cs.AI] UPDATED) 

arxiv.org/abs/2312.14890

0
arXiv - CSCL

Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data. (arXiv:2311.17492v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.17492

0
arXiv - CSCL

Multistage Collaborative Knowledge Distillation from Large Language Models for Semi-Supervised Sequence Generation. (arXiv:2311.08640v2 [cs.CL] UPDATED) 

arxiv.org/abs/2311.08640

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