Show newer
arXiv - CSCL

SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations. (arXiv:2311.00273v1 [cs.CL]) 

arxiv.org/abs/2311.00273

0
arXiv - CSCL

Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?. (arXiv:2311.00268v1 [cs.CL]) 

arxiv.org/abs/2311.00268

0
arXiv - CSCL

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents. (arXiv:2311.00262v1 [cs.CL]) 

arxiv.org/abs/2311.00262

0
arXiv - CSCL

Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis. (arXiv:2311.00258v1 [cs.CL]) 

arxiv.org/abs/2311.00258

0
arXiv - CSCL

The Mystery and Fascination of LLMs: A Comprehensive Survey on the Interpretation and Analysis of Emergent Abilities. (arXiv:2311.00237v1 [cs.CL]) 

arxiv.org/abs/2311.00237

0
arXiv - CSCL

Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions. (arXiv:2311.00233v1 [cs.CL]) 

arxiv.org/abs/2311.00233

0
arXiv - CSCL

Is GPT Powerful Enough to Analyze the Emotions of Memes?. (arXiv:2311.00223v1 [cs.CL]) 

arxiv.org/abs/2311.00223

0
arXiv - CSCL

Transformers as Recognizers of Formal Languages: A Survey on Expressivity. (arXiv:2311.00208v1 [cs.LG]) 

arxiv.org/abs/2311.00208

0
arXiv - CSCL

Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering. (arXiv:2311.00204v1 [cs.CL]) 

arxiv.org/abs/2311.00204

0
arXiv - CSCL

XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision. (arXiv:2311.00189v1 [cs.CL]) 

arxiv.org/abs/2311.00189

0
arXiv - CSCL

ChipNeMo: Domain-Adapted LLMs for Chip Design. (arXiv:2311.00176v1 [cs.CL]) 

arxiv.org/abs/2311.00176

0
arXiv - CSCL

Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield. (arXiv:2311.00172v1 [cs.CL]) 

arxiv.org/abs/2311.00172

0
arXiv - CSCL

Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language. (arXiv:2311.00161v1 [cs.CL]) 

arxiv.org/abs/2311.00161

0
arXiv - CSCL

Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks. (arXiv:2311.00159v1 [cs.CL]) 

arxiv.org/abs/2311.00159

0
arXiv - CSCL

Two-Stage Classifier for Campaign Negativity Detection using Axis Embeddings: A Case Study on Tweets of Political Users during 2021 Presidential Election in Iran. (arXiv:2311.00143v1 [cs.LG]) 

arxiv.org/abs/2311.00143

0
arXiv - CSCL

On the effect of curriculum learning with developmental data for grammar acquisition. (arXiv:2311.00128v1 [cs.CL]) 

arxiv.org/abs/2311.00128

0
arXiv - CSCL

BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B. (arXiv:2311.00117v1 [cs.CL]) 

arxiv.org/abs/2311.00117

0
arXiv - CSCL

BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text. (arXiv:2311.00116v1 [cs.CL]) 

arxiv.org/abs/2311.00116

0
arXiv - CSCL

The Generative AI Paradox: "What It Can Create, It May Not Understand". (arXiv:2311.00059v1 [cs.AI]) 

arxiv.org/abs/2311.00059

0
arXiv - CSCL

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?. (arXiv:2311.00047v1 [cs.AI]) 

arxiv.org/abs/2311.00047

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