Show newer

Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models. (arXiv:2307.14430v1 [cs.CL] CROSS LISTED) 

Hexatagging: Projective Dependency Parsing as Tagging. (arXiv:2306.05477v1 [cs.CL] CROSS LISTED) 

A Geometric Notion of Causal Probing. (arXiv:2307.15054v2 [cs.CL] UPDATED) 

Gzip versus bag-of-words for text classification with KNN. (arXiv:2307.15002v2 [cs.CL] UPDATED) 

XDLM: Cross-lingual Diffusion Language Model for Machine Translation. (arXiv:2307.13560v2 [cs.CL] UPDATED) 

Applying QNLP to sentiment analysis in finance. (arXiv:2307.11788v2 [cs.CL] UPDATED) 

L-Eval: Instituting Standardized Evaluation for Long Context Language Models. (arXiv:2307.11088v2 [cs.CL] UPDATED) 

ChatGPT is Good but Bing Chat is Better for Vietnamese Students. (arXiv:2307.08272v3 [cs.CL] UPDATED) 

Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations. (arXiv:2307.06576v4 [cs.IR] UPDATED) 

Interpreting deep embeddings for disease progression clustering. (arXiv:2307.06060v2 [stat.ML] UPDATED) 

Measuring Lexical Diversity in Texts: The Twofold Length Problem. (arXiv:2307.04626v2 [cs.CL] UPDATED) 

Lost in the Middle: How Language Models Use Long Contexts. (arXiv:2307.03172v2 [cs.CL] UPDATED) 

What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?. (arXiv:2307.02469v2 [cs.CV] UPDATED) 

Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text. (arXiv:2306.03557v2 [cs.CL] UPDATED) 

Syntax-aware Hybrid prompt model for Few-shot multi-modal sentiment analysis. (arXiv:2306.01312v2 [cs.CL] UPDATED) 

Column Type Annotation using ChatGPT. (arXiv:2306.00745v2 [cs.CL] UPDATED) 

Forgotten Knowledge: Examining the Citational Amnesia in NLP. (arXiv:2305.18554v2 [cs.CL] UPDATED) 

A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions. (arXiv:2305.18339v2 [cs.CY] UPDATED) 

Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective. (arXiv:2305.17760v5 [cs.CL] UPDATED) 

Science in the Era of ChatGPT, Large Language Models and Generative AI: Challenges for Research Ethics and How to Respond. (arXiv:2305.15299v4 [cs.CY] UPDATED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.