Kalender

• Fanny Walldén: Fine-Tuning Language Models with Preferences for Text Summarization Tasks: A Comparative Study of Reinforcement Learning from Human Feedback and Direct Preference Optimization

  3 jun

  Examensarbete

  onsdag 2026-06-03, 08.00 - 08.45

  Medverkande: Fanny Walldén

  Plats: Albano, Mittag-Leffler room, floor 3, house 1

  Respondent: Fanny Walldén

  2026-06-03T08:00:00.000+02:00 2026-06-03T08:45:00.000+02:00 Fanny Walldén: Fine-Tuning Language Models with Preferences for Text Summarization Tasks: A Comparative Study of Reinforcement Learning from Human Feedback and Direct Preference Optimization (Examensarbete) Albano, Mittag-Leffler room, floor 3, house 1 (KTH, Stockholm, Sweden)Fanny Walldén: Fine-Tuning Language Models with Preferences for Text Summarization Tasks: A Comparative Study of Reinforcement Learning from Human Feedback and Direct Preference Optimization (Examensarbete)