Show newer
arXiv - CSCL

RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge. (arXiv:2311.08147v1 [cs.CL]) 

arxiv.org/abs/2311.08147

0
arXiv - CSCL

Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval. (arXiv:2311.08143v1 [cs.CL]) 

arxiv.org/abs/2311.08143

0
arXiv - CSCL

Memory-efficient Stochastic methods for Memory-based Transformers. (arXiv:2311.08123v1 [cs.LG]) 

arxiv.org/abs/2311.08123

0
arXiv - CSCL

Insights into Classifying and Mitigating LLMs' Hallucinations. (arXiv:2311.08117v1 [cs.CL]) 

arxiv.org/abs/2311.08117

0
arXiv - CSCL

Improving hateful memes detection via learning hatefulness-aware embedding space through retrieval-guided contrastive learning. (arXiv:2311.08110v1 [cs.CL]) 

arxiv.org/abs/2311.08110

0
arXiv - CSCL

SAIE Framework: Support Alone Isn't Enough -- Advancing LLM Training with Adversarial Remarks. (arXiv:2311.08107v1 [cs.CL]) 

arxiv.org/abs/2311.08107

0
arXiv - CSCL

Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models. (arXiv:2311.08106v1 [cs.CL]) 

arxiv.org/abs/2311.08106

0
arXiv - CSCL

DiLoCo: Distributed Low-Communication Training of Language Models. (arXiv:2311.08105v1 [cs.LG]) 

arxiv.org/abs/2311.08105

0
arXiv - CSCL

Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction. (arXiv:2311.08103v1 [cs.CL]) 

arxiv.org/abs/2311.08103

0
arXiv - CSCL

Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts. (arXiv:2311.08097v1 [cs.CL]) 

arxiv.org/abs/2311.08097

0
arXiv - CSCL

Spot: A Natural Language Interface for Geospatial Searches in OSM. (arXiv:2311.08093v1 [cs.CL]) 

arxiv.org/abs/2311.08093

0
arXiv - CSCL

Align after Pre-train: Improving Multilingual Generative Models with Cross-lingual Alignment. (arXiv:2311.08089v1 [cs.CL]) 

arxiv.org/abs/2311.08089

0
arXiv - CSCL

Data and models for stance and premise detection in COVID-19 tweets: insights from the Social Media Mining for Health (SMM4H) 2022 shared task. (arXiv:2311.08057v1 [cs.CL]) 

arxiv.org/abs/2311.08057

0
arXiv - CSCL

Adversarial Preference Optimization. (arXiv:2311.08045v1 [cs.CL]) 

arxiv.org/abs/2311.08045

0
arXiv - CSCL

Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models. (arXiv:2311.08011v1 [cs.CL]) 

arxiv.org/abs/2311.08011

0
arXiv - CSCL

Distantly-Supervised Named Entity Recognition with Uncertainty-aware Teacher Learning and Student-student Collaborative Learning. (arXiv:2311.08010v1 [cs.CL]) 

arxiv.org/abs/2311.08010

0
arXiv - CSCL

TempTabQA: Temporal Question Answering for Semi-Structured Tables. (arXiv:2311.08002v1 [cs.CL]) 

arxiv.org/abs/2311.08002

0
arXiv - CSCL

A Comparative Analysis of the COVID-19 Infodemic in English and Chinese: Insights from Social Media Textual Data. (arXiv:2311.08001v1 [cs.SI]) 

arxiv.org/abs/2311.08001

0
arXiv - CSCL

How Well Do Text Embedding Models Understand Syntax?. (arXiv:2311.07996v1 [cs.CL]) 

arxiv.org/abs/2311.07996

0
arXiv - CSCL

A Survey on Language Models for Code. (arXiv:2311.07989v1 [cs.CL]) 

arxiv.org/abs/2311.07989

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