Multi-Personality Generation of LLMs at Decoding-time
Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibility and robustness. In this paper, we propose a novel Multi-Personality Generation (MPG) framework under the decoding-time combination paradigm. It flexibly controls multi-personality without relying on scarce multi-dimensional models or extra training, leveraging implicit density ratios in single-dimensional models as a "free lunch" to reformulate the task as sampling from a target strategy aggregating these ratios. To implement MPG efficiently, we design Speculative Chunk-level based Rejection sampling (SCR), which generates responses in chunks and parallelly validates them via estimated thresholds within a sliding window. This significantly reduces computational overhead while maintaining high-quality generation. Experiments on MBTI personality and Role-Playing demonstrate the effectiveness of MPG, showing improvements up to 16%-18%. Code and data are available at https://github.com/Libra117/MPG .
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs
Personality is increasingly important in large language models (LLMs), as it shapes users' trust, engagement, and emotional experiences. While the Myers--Briggs Type Indicator (MBTI) has emerged as a common framework for…
Tailoring Personality Traits in Large Language Models via Unsupervisedly-Built Personalized Lexicons
Personality plays a pivotal role in shaping human expression patterns, thus regulating the personality of large language models (LLMs) holds significant potential in enhancing the user experience of LLMs. Previous method…
Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs
Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psychology, they often can emulate human beh…
Decision MakingDynamic Generation of Personalities with Large Language Models
In the realm of mimicking human deliberation, large language models (LLMs) show promising performance, thereby amplifying the importance of this research area. Deliberation is influenced by both logic and personality. Ho…
Personality GenerationLMLPA: Language Model Linguistic Personality Assessment
Large Language Models (LLMs) are increasingly used in everyday life and research. One of the most common use cases is conversational interactions, enabled by the language generation capabilities of LLMs. Just as between …
Language ModelingLanguage ModellingmodelText Generation