Show newer
arXiv - CSCL

On the Exploitability of Reinforcement Learning with Human Feedback for Large Language Models. (arXiv:2311.09641v1 [cs.AI]) 

arxiv.org/abs/2311.09641

0
arXiv - CSCL

Evaluating In-Context Learning of Libraries for Code Generation. (arXiv:2311.09635v1 [cs.CL]) 

arxiv.org/abs/2311.09635

0
arXiv - CSCL

Online Continual Knowledge Learning for Language Models. (arXiv:2311.09632v1 [cs.CL]) 

arxiv.org/abs/2311.09632

0
arXiv - CSCL

From Scroll to Misbelief: Modeling the Unobservable Susceptibility to Misinformation on Social Media. (arXiv:2311.09630v1 [cs.CL]) 

arxiv.org/abs/2311.09630

0
arXiv - CSCL

CRISPR: Eliminating Bias Neurons from an Instruction-following Language Model. (arXiv:2311.09627v1 [cs.AI]) 

arxiv.org/abs/2311.09627

0
arXiv - CSCL

Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning. (arXiv:2311.09619v1 [cs.CL]) 

arxiv.org/abs/2311.09619

0
arXiv - CSCL

Simulating Opinion Dynamics with Networks of LLM-based Agents. (arXiv:2311.09618v1 [physics.soc-ph]) 

arxiv.org/abs/2311.09618

0
arXiv - CSCL

On Retrieval Augmentation and the Limitations of Language Model Training. (arXiv:2311.09615v1 [cs.CL]) 

arxiv.org/abs/2311.09615

0
arXiv - CSCL

Digital Socrates: Evaluating LLMs through explanation critiques. (arXiv:2311.09613v1 [cs.CL]) 

arxiv.org/abs/2311.09613

0
arXiv - CSCL

Efficient End-to-End Visual Document Understanding with Rationale Distillation. (arXiv:2311.09612v1 [cs.CV]) 

arxiv.org/abs/2311.09612

0
arXiv - CSCL

GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks. (arXiv:2311.09606v1 [cs.CL]) 

arxiv.org/abs/2311.09606

0
arXiv - CSCL

Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals. (arXiv:2311.09605v1 [cs.CL]) 

arxiv.org/abs/2311.09605

0
arXiv - CSCL

SCORE: A framework for Self-Contradictory Reasoning Evaluation. (arXiv:2311.09603v1 [cs.CL]) 

arxiv.org/abs/2311.09603

0
arXiv - CSCL

Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion. (arXiv:2311.09602v1 [cs.CL]) 

arxiv.org/abs/2311.09602

0
arXiv - CSCL

Multi-Step Dialogue Workflow Action Prediction. (arXiv:2311.09593v1 [cs.CL]) 

arxiv.org/abs/2311.09593

0
arXiv - CSCL

LifeTox: Unveiling Implicit Toxicity in Life Advice. (arXiv:2311.09585v1 [cs.CL]) 

arxiv.org/abs/2311.09585

0
arXiv - CSCL

Enhancing Medical Text Evaluation with GPT-4. (arXiv:2311.09581v1 [cs.CL]) 

arxiv.org/abs/2311.09581

0
arXiv - CSCL

MMOE: Mixture of Multimodal Interaction Experts. (arXiv:2311.09580v1 [cs.CL]) 

arxiv.org/abs/2311.09580

0
arXiv - CSCL

Crafting In-context Examples according to LMs' Parametric Knowledge. (arXiv:2311.09579v1 [cs.CL]) 

arxiv.org/abs/2311.09579

0
arXiv - CSCL

Tied-Lora: Enhacing parameter efficiency of LoRA with weight tying. (arXiv:2311.09578v1 [cs.CL]) 

arxiv.org/abs/2311.09578

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