Related papers: PERSONA: Dynamic and Compositional Inference-Time …

Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning…

While persona-driven large language models (LLMs) and prompt-based text-to-speech (TTS) systems have advanced significantly, a usability gap arises when users attempt to generate voices matching their desired personas from implicit…

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

The recent introduction of the Assistants API highlights its potential for large language models (LLMs) in role-playing agents (RPA). However, maintaining consistent character personas remains a significant challenge due to variability in…

Large language models are increasingly used as behavioral simulators, but it remains unclear when their outputs reflect human-like cognitive mechanisms rather than prompt-sensitive surface patterns. We study this question through the…

Personalized review response generation presents a significant challenge in domains where user information is limited, such as food delivery platforms. While large language models (LLMs) offer powerful text generation capabilities, they…

In this work, we introduce the task of life-long personalization of large language models. While recent mainstream efforts in the LLM community mainly focus on scaling data and compute for improved capabilities of LLMs, we argue that it is…

Large Language Models (LLMs) used in creative workflows can reinforce stereotypes and perpetuate inequities, making fairness auditing essential. Existing methods rely on constrained tasks and fixed benchmarks, leaving open-ended creative…

Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches the given textual descriptions. While most of the current methods treat the task as a holistic visual and textual feature…

While Large Language Model (LLM)-based agents can be used to create highly engaging interactive applications through prompting personality traits and contextual data, effectively assessing their personalities has proven challenging. This…

Large Language Models (LLMs) have demonstrated promising capabilities to generate responses that simulate consistent personality traits. Despite the major attempts to analyze personality expression through output-based evaluations, little…

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of…

Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information is often provided as static descriptions that miss the values, experiences, and contextual…

Personalized Large Language Models (LLMs) facilitate more natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained by limited controllability and high resource demands.…

Fine-grained personas have recently been used for generating 'diverse' synthetic data for pre-training and supervised fine-tuning of Large Language Models (LLMs). In this work, we measure the diversity of persona-driven synthetically…

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). However, achieving authentic alignment…

Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with…

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of…

Activation steering offers a computationally efficient mechanism for controlling Large Language Models (LLMs) without fine-tuning. While effectively controlling target traits (e.g., persona), coherency degradation remains a major obstacle…

Learning analytics (LA) draws from the learning sciences to interpret learner behavior and inform system design. Yet, past personalization remains largely at the content or performance level (during learner-system interactions), overlooking…