EPISODE · May 23, 2025 · 15 MIN
Personalizing LLMs via Decode-Time Human Preference Optimization
from Best AI papers explained · host Enoch H. Kang
This paper introduces PANDA, a novel approach to personalizing large language models (LLMs) at the point of generating text, known as inference time. Unlike traditional methods that require costly retraining for each new preference, PANDA dynamically adjusts an LLM's output based on learned user preferences without altering the core model. By using context-aware preference weights and reward models, PANDA enables flexible and efficient tailoring of LLM responses to individual needs, validated through experiments showing improved performance on personalized tasks compared to existing alignment techniques. This method represents a significant step towards scalable and dynamic personalization of LLMs.
What this episode covers
This paper introduces PANDA, a novel approach to personalizing large language models (LLMs) at the point of generating text, known as inference time. Unlike traditional methods that require costly retraining for each new preference, PANDA dynamically adjusts an LLM's output based on learned user preferences without altering the core model. By using context-aware preference weights and reward models, PANDA enables flexible and efficient tailoring of LLM responses to individual needs, validated through experiments showing improved performance on personalized tasks compared to existing alignment techniques. This method represents a significant step towards scalable and dynamic personalization of LLMs.
NOW PLAYING
Personalizing LLMs via Decode-Time Human Preference Optimization
No transcript for this episode yet
Similar Episodes
Mar 31, 2026 ·54m
Mar 27, 2026 ·14m
Mar 24, 2026 ·42m
Mar 20, 2026 ·42m
Mar 17, 2026 ·41m
Mar 13, 2026 ·44m