UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
This addresses the need for precise personality regulation in LLMs to enhance user experiences, representing an incremental improvement over existing methods.
The paper tackled the problem of inefficient and imprecise personality control in large language models by proposing UPLex, a method using an unsupervisedly-built personalized lexicon during decoding, which demonstrated remarkable effectiveness for fine-grained manipulation.
Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs) holds significant potential in enhancing their user experiences. Previous approaches either relied on fine-tuning LLMs on specific corpora or required manually crafted prompts to evoke specific personalities from LLMs. However, the former is inefficient and costly, while the latter cannot precisely manipulate personality traits at a fine-grained level. To address these challenges, we propose UPLex, a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM's personality traits. UPL can be constructed from a newly built situational judgment test dataset in an unsupervised fashion, and used to modulate the personality expression of LLMs by dynamically altering their predicted probability of upcoming words in a pluggable fashion. Extensive experimentation demonstrates the remarkable effectiveness and pluggability of our method for fine-grained manipulation of LLMs' personalities.