NLP Wiki

User Tools

Site Tools

Trace: • rnn • nn_tricks • human-in-the-loop
nlp:instruction-tuning

Differences

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

Link to this comparison view

Both sides previous revisionPrevious revision
nlp:instruction-tuning [2025/06/01 22:56] – [Papers] jmflanignlp:instruction-tuning [2025/06/01 22:58] (current) – [Papers] jmflanig
Line 41: Line 41:
     * [[https://arxiv.org/pdf/2402.18571|Wang et al 2024 - Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards]]     * [[https://arxiv.org/pdf/2402.18571|Wang et al 2024 - Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards]]
   * **Analyzing, Filtering, or Improving Preference Data**   * **Analyzing, Filtering, or Improving Preference Data**
-    * [[https://arxiv.org/pdf/2505.23114|Lee et al 2025 - Dataset Cartography for Large Language Model Alignment: Mapping and Diagnosing Preference Data]]+    * [[https://arxiv.org/pdf/2505.23114|Lee et al 2025 - Dataset Cartography for Large Language Model Alignment: Mapping and Diagnosing Preference Data]] Applies dataset cartography ([[https://arxiv.org/pdf/2009.10795|Swayamdipta 2020]]) to preference data
  
 ===== Datasets ===== ===== Datasets =====
nlp/instruction-tuning.1748818603.txt.gz · Last modified: 2025/06/01 22:56 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki