Evaluating Approaches to Personalizing Language Models
In this work, we consider the problem of personalizing language models, that is, building language models that are tailored to the writing style of an individual. Because training language models requires a large amount of text, and individuals do not necessarily possess a large corpus of their writing that could be used for training, approaches to personalizing language models must be able to rely on only a small amount of text from any one user. In this work, we compare three approaches to personalizing a language model that was trained on a large background corpus using a relatively small amount of text from an individual user. We evaluate these approaches using perplexity, as well as two measures based on next word prediction for smartphone soft keyboards. Our results show that when only a small amount of user-specific text is available, an approach based on priming gives the most improvement, while when larger amounts of user-specific text are available, an approach based on language model interpolation performs best. We carry out further experiments to show that these approaches to personalization outperform language model adaptation based on demographic factors.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
LaMP: When Large Language Models Meet Personalization
This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs. LaMP…
Language ModelingLanguage ModellingNatural Language UnderstandingRetrieval+3Hypernetworks for Personalizing ASR to Atypical Speech
Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models to atypical speech. However, these approaches assume a priori …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)parameter-efficient fine-tuningspeech-recognition+1Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize …
Knowledge DistillationLanguage ModelingLanguage ModellingRetrievalLoRe: Personalizing LLMs via Low-Rank Reward Modeling
Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning from human feedback (RLHF) approaches ofte…
Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models
Privacy-preserving methods for personalizing large language models (LLMs) are relatively under-explored. There are two schools of thought on this topic: (1) generating personalized outputs by personalizing the input prom…
parameter-efficient fine-tuningPrivacy PreservingRAGRetrieval