NLP Wiki

User Tools

Site Tools

Trace: • efficient_nns • reinforcement_learning • hyperparameter_tuning • generalization_in_deep_learning • coreference_resolution • tokenization • knowledge_distillation • explainability • language_model • state-space_models
nlp:alignment

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
nlp:alignment [2025/04/30 06:02] – [Overviews] jmflanignlp:alignment [2025/06/03 00:26] (current) – [People] jmflanig
Line 4: Line 4:
   * [[https://arxiv.org/pdf/2309.15025.pdf|Shen et al 2023 - Large Language Model Alignment: A Survey]]   * [[https://arxiv.org/pdf/2309.15025.pdf|Shen et al 2023 - Large Language Model Alignment: A Survey]]
   * [[https://arxiv.org/pdf/2310.19852|Ji et al 2023 - AI Alignment: A Comprehensive Survey]]   * [[https://arxiv.org/pdf/2310.19852|Ji et al 2023 - AI Alignment: A Comprehensive Survey]]
 +  * [[https://arxiv.org/pdf/2404.09932|Anwar et al 2024 - Foundational Challenges in Assuring Alignment and Safety of Large Language Models]]
  
 ===== Blog Posts, etc ===== ===== Blog Posts, etc =====
Line 18: Line 19:
  
 ===== People ===== ===== People =====
 +  * [[https://scholar.google.com/citations?user=kV9XRxYAAAAJ&hl=en|Sam Bowman]]
   * [[https://scholar.google.com/citations?user=czyretsAAAAJ&hl=en|Dan Hendrycks]]   * [[https://scholar.google.com/citations?user=czyretsAAAAJ&hl=en|Dan Hendrycks]]
  
Line 24: Line 26:
   * [[Instruction-Tuning]] Instruction-tuning is often similar to alignment, but alignment is broader.  Instruction-tuning methods often falls under alignment.   * [[Instruction-Tuning]] Instruction-tuning is often similar to alignment, but alignment is broader.  Instruction-tuning methods often falls under alignment.
   * [[Language Model]]   * [[Language Model]]
 +  * [[LLM Safety]] 
 +  * [[ml:Mechanistic Interpretability]]
nlp/alignment.1745992975.txt.gz · Last modified: 2025/04/30 06:02 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki