Tootfinder

Co-persona: Leveraging LLMs and Expert Collaboration to Understand User Personas through Social Media Data Analysis
Min Yin, Haoyu Liu, Boyi Lian, Chunlei Chai
https://arxiv.org/abs/2506.18269

Co-persona: Leveraging LLMs and Expert Collaboration to Understand User Personas through Social Media Data Analysis
This study introduces \textsc{Co-Persona}, a framework bridging large-scale social media analysis and user understanding via integration of Large Language Models (LLMs) and expert validation. Through a case study of B.Co, a Chinese manufacturer, we applied \textsc{Co-Persona} to bedside lamp development by analyzing 38 million posts from Xiao Hongshu. Our multi-stage NLP processing revealed five user personas based on nighttime behaviors: Health Aficionados, Night Owls, Interior Decorators, Chi…

Author and actor Yrsa Daley-Ward on balancing the public and the private
#creativity
https://thecreativeindependent.com/peo

Author and actor Yrsa Daley-Ward on balancing the public and the private – The Creative Independent
Author, actor, and screenwriter Yrsa Daley-Ward discusses trusting her work, finding ways to self-regulate, and debunking the illusion of an Instagram persona.

Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
Ayato Kitadai, Yusuke Fukasawa, Nariaki Nishino
https://arxiv.org/abs/2508.18600 https://…

Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
Large language models (LLMs) are increasingly used to simulate human decision-making, but their intrinsic biases often diverge from real human behavior--limiting their ability to reflect population-level diversity. We address this challenge with a persona-based approach that leverages individual-level behavioral data from behavioral economics to adjust model biases. Applying this method to the ultimatum game--a standard but difficult benchmark for LLMs--we observe improved alignment between sim…

Anthropic details "persona vectors", patterns of activity within an AI model's neural network that control its character traits, such as evil and sycophancy (Anthropic)
https://www.anthropic.com/research/persona-vectors

Persona vectors: Monitoring and controlling character traits in language models
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior

PosterMate: Audience-driven Collaborative Persona Agents for Poster Design
Donghoon Shin, Daniel Lee, Gary Hsieh, Gromit Yeuk-Yin Chan
https://arxiv.org/abs/2507.18572 https://

PosterMate: Audience-driven Collaborative Persona Agents for Poster Design
Poster designing can benefit from synchronous feedback from target audiences. However, gathering audiences with diverse perspectives and reconciling them on design edits can be challenging. Recent generative AI models present opportunities to simulate human-like interactions, but it is unclear how they may be used for feedback processes in design. We introduce PosterMate, a poster design assistant that facilitates collaboration by creating audience-driven persona agents constructed from marketi…

visionOS 26: Bessere Persona, mehr Spatial-Content und erstmals Widgets
Von visionOS 2.5 direkt auf visionOS 26: Apple bringt zahlreiche Neuerungen für sein Headset Vision Pro – mehr, als viele erwartet hätten.

Louis Armstrong: The US jazz icon with a 'controversial' legacy? If you ask me, Pops was grinnin' 'cause he was winnin'! Micheal Ray said to me, there were only two times in America when it was OK to be black and happy; the other time was Disco.
Gold plated bathroom, Richard Nixon smuggles your stash, and (fuck Miles, he was too coked to have sense) not one detractor, even his ex and his mistress joined his wife at his funeral. Yeah, 'controversial' 🙄
…

Ya abrió Pequeño Mundo Tibšs

LLM-Based Social Simulations Require a Boundary
Zengqing Wu, Run Peng, Takayuki Ito, Chuan Xiao
https://arxiv.org/abs/2506.19806 https://

LLM-Based Social Simulations Require a Boundary
This position paper argues that large language model (LLM)-based social simulations should establish clear boundaries to meaningfully contribute to social science research. While LLMs offer promising capabilities for modeling human-like agents compared to traditional agent-based modeling, they face fundamental limitations that constrain their reliability for social pattern discovery. The core issue lies in LLMs' tendency towards an ``average persona'' that lacks sufficient behavioral heterogene…

Warum heißt es laktoseintolerant und nicht persona non gratin?

Oh wow, there's a new Mr. Plinkett video!
(For those who don't know, that "movie critic" persona was created for an epic takedown of StarWars episodes 1-3 in the early era of youtube. For me and probably many others it was the first time they saw funny but smart long-form video essays about culture and media.)
https://www.

Using AI for User Representation: An Analysis of 83 Persona Prompts
Joni Salminen, Danial Amin, Bernard Jansen
https://arxiv.org/abs/2508.13047 https://arx…

Using AI for User Representation: An Analysis of 83 Persona Prompts
We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or concise persona descriptions, which deviates from the tradition of creating rich, informative, and rounded persona profiles. Text is the most common format for generated persona attributes, followed by numbers. Text and numbers are often generated together, a…

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
Geonhee Sim, Gyeongsik Moon
https://arxiv.org/abs/2508.09973 https://

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
Two major approaches exist for creating animatable human avatars. The first, a 3D-based approach, optimizes a NeRF- or 3DGS-based avatar from videos of a single person, achieving personalization through a disentangled identity representation. However, modeling pose-driven deformations, such as non-rigid cloth deformations, requires numerous pose-rich videos, which are costly and impractical to capture in daily life. The second, a diffusion-based approach, learns pose-driven deformations from la…

🇺🇦 #NowPlaying on KEXP's #StreetSounds
Tyler, The Creator:
🎵 Sucka Free
#Tyler #TheCreator
#newRelease 🆕 album
https://reyrzy.bandcamp.com/track/sucka-free-love-tyler-the-creator-x-persona-4-mashup
https://open.spotify.com/track/7DIMKlmJ0CL6eROkbptoqi

"Sweeney’s right that there’s no unpressing the AI button; companies are going to make these things until the bottom falls out. Epic’s demo is just one more uninspiring bit of buzzwordery to add to the pile."
(Original title: Unreal’s AI Demo Had No Point)
https://aftermath.site/…

Unreal's AI Demo Had No Point - Aftermath
We have Portal at home

Human Voice is Unique
Rita Singh, Bhiksha Raj
https://arxiv.org/abs/2506.18182 https://arxiv.org/pdf/2506.18182

Human Voice is Unique
Voice is increasingly being used as a biometric entity in many applications. These range from speaker identification and verification systems to human profiling technologies that attempt to estimate myriad aspects of the speaker's persona from their voice. However, for an entity to be a true biometric identifier, it must be unique. This paper establishes a first framework for calculating the uniqueness of human voice objectively. The approach in this paper is based on statistical considerations…

83 años cumple hoy la persona viva mšs influyente e importante en la historia del rock. Un genio como pocos que cambió la historia de la música con The Beatles y ha hecho una extensa carrera con Wings y como solista. ¡Feliz #cumpleañosRockero para Paul McCartney!
#PaulMcCartney

Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?
Junhyuk Choi, Hyeonchu Park, Haemin Lee, Hyebeen Shin, Hyun Joung Jin, Bugeun Kim
https://arxiv.org/abs/2508.03262

Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?
Recent advances in Large Language Models (LLMs) have generated significant interest in their capacity to simulate human-like behaviors, yet most studies rely on fictional personas rather than actual human data. We address this limitation by evaluating LLMs' ability to predict individual economic decision-making using Pay-What-You-Want (PWYW) pricing experiments with real 522 human personas. Our study systematically compares three state-of-the-art multimodal LLMs using detailed persona informati…

Towards Using Personas in Requirements Engineering: What Has Been Changed Recently?
Chowdhury Shahriar Muzammel, Maria Spichkova, James Harland
https://arxiv.org/abs/2507.15197

Towards Using Personas in Requirements Engineering: What Has Been Changed Recently?
In requirements engineering (RE), personas are now being used to represent user expectations and needs. This systematic mapping study (SMS) aims to explore the most recent studies and to cover recent changes in trends, especially related to the recent evolution of Generative AI approaches. Our SMS covers the period between April 2023 and April 2025. We identified 22 relevant publications and analysed persona representation, construction, validation, as well as RE activities covered by personas.…

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
Zheng Zhang, Peilin Zhao, Deheng Ye, Hao Wang
https://arxiv.org/abs/2507.22171 https://arxiv.org/pd…

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM safety. Previous jailbreak approaches have mainly focused on direct manipulations of harmful intent, with limited attention to the impact of persona prompts. In this study, we systematically explore the efficacy of persona prompts in compromising LLM defenses. We p…

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit
Paulo Salem, Robert Sim, Christopher Olsen, Prerit Saxena, Rafael Barcelos, Yi Ding
https://arxiv.org/abs/2507.09788

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit
Recent advances in Large Language Models (LLM) have led to a new class of autonomous agents, renewing and expanding interest in the area. LLM-powered Multiagent Systems (MAS) have thus emerged, both for assistive and simulation purposes, yet tools for realistic human behavior simulation -- with its distinctive challenges and opportunities -- remain underdeveloped. Existing MAS libraries and tools lack fine-grained persona specifications, population sampling facilities, experimentation support, …

Yo creo que terminaríamos antes si encarcelamos preventivamente a toda persona que sea elegida para un cargo político de cierto rango. Total, van a terminar ante el juez tarde o temprano, qué les importarš.

𝐉𝐮𝐬𝐭 𝐟𝐢𝐧𝐢𝐬𝐡𝐞𝐝: 𝑃𝑒𝑟𝑠𝑜𝑛𝑎 5 𝑅𝑜𝑦𝑎𝑙
#games #persona #jrpg #rpg

“Our method … is somewhat counterintuitive: we actually steer the model toward undesirable persona vectors... The method is loosely analogous to … a vaccine—by giving the model a dose of “evil,” for instance, we make it more resilient to encountering “evil” training data. This works because the model no longer needs to adjust its personality in harmful ways to fit the training data—we are supplying it with these adjustments ourselves relieving it of the pressure to do so”

Persona vectors: Monitoring and controlling character traits in language models
A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior

Roblox partners with Persona to estimate user ages and verify they are 13 , renames Friends to Connections, and says 13 users can message Trusted Connections (Jay Peters/The Verge)
https://www.theverge.com/news/708670/roblox-trusted-connections-age-est…

Roblox will require a facial scan or government ID to have unfiltered chats
Roblox will let people make “Trusted Connections” to chat more freely, but will require that they use a new age estimation tool to verify that they’re over 13.

The new ChatGPT-5 persona is a straight-up asshole 👍

I wonder when other nations will begin ejecting government officials - including FFOTUS - and declare them "persona non grata"?

I wanna change artist name to a sexier more professional one. Also this whole online persona I created doesn't fit me anymore. Should I take down my website? It's a big expense and it doesn't satisfy me anymore. Was fun but I think its time has come.

Evaluating Prompt-Driven Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Geng Liu, Li Feng, Carlo Alberto Bono, Songbo Yang, Mengxiao Zhu, Francesco Pierri
https://arxiv.org/abs/2506.04975

Evaluating Prompt-Driven Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards
Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. Yet, limited attention has been given to persona-driven toxicity in non-Western contexts, particularly in Chinese-based LLMs. In this paper, we perform a large-scale, systematic analysis of how persona assignment influences refusal behavior and response toxicity in Qwen, a widely-used Chinese language model. Utilizing fine-tuned BERT classifiers…

Geert Wilders posted an islamophic image in a tweet a few days ago and is now being sued for it.
The thing is, the image is clearly AI generated. This means that the prompt for it is still around somewhere.
Under US discovery, that prompt would certainly be made public; possibly in the Dutch system as well.
This suggests some interesting possibilities. First, if Wilders made the image himself, his language in the prompt may have been more candid than his public persona.

Calamus 27 O love!
Odd little poem. On the surface it's a celebration of reinvention, of metaphorically dying and leaving your corpse behind, "always living". I don't find it particularly compelling but it's a mood.
I can't honestly find a particularly gay reading here. Broadly speaking maybe, "coming out" is a kind of reinvention gay people do, leaving our old closeted persona dead and gone. I wouldn't argue Whitman is talking about that though.
One odd thing is the 1860 poem starts "O love!", but there's no love mentioned in the rest of the text. Whitman removed this line in later versions. So who or what is the love referring to?

LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
Seth Karten, Wenzhe Li, Zihan Ding, Samuel Kleiner, Yu Bai, Chi Jin
https://arxiv.org/abs/2507.15815

LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. At the lower level, bounded rational worker agents -- instantiated as persona-conditioned prompts sampled from U.S. Census-calibrated income and demographic statistics -- choose labor supply to maximize text-based utility functions learned in-context. At the upper level, a planner agent employs in-context reinforcement…

Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
Guilherme Guerino, Luiz Rodrigues, Bruna Capeleti, Rafael Ferreira Mello, Andr\'e Freire, Luciana Zaina
https://arxiv.org/abs/2506.16345

Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
Heuristic evaluation is a widely used method in Human-Computer Interaction (HCI) to inspect interfaces and identify issues based on heuristics. Recently, Large Language Models (LLMs), such as GPT-4o, have been applied in HCI to assist in persona creation, the ideation process, and the analysis of semi-structured interviews. However, considering the need to understand heuristics and the high degree of abstraction required to evaluate them, LLMs may have difficulty conducting heuristic evaluation…

How Palantir won over US lawmakers, leveraging geopolitical crises, technological trends, and DC connections, as CEO Alex Karp adopts a persona not unlike Trump (Wall Street Journal)
https://www.wsj.com/tech/palantir-pltr-sto

Amigas y amigos latinoamericanos y especialmente de Chile, ¿Conocen alguna iniciativa comunitaria para proveer servicios en línea que sea de la región? Me refiero a mšs que un esfuerzo individual de una sola persona o una instancia de alguna plataforma, sino que sea realmente comunitaria y que entregue varios servicios con servidores en la zona.
Estoy pensando en algo como lo que hacen en disroot, pero puede ser a menor escala.

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/6]:
- OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Onli...
Wang, Lu, Li, Amini, Sun, Bart, Lyu, Gesi, Wang, Huang, Su, Ehsan, Alikhani, Li, Chilton, Wang
…

Creating a customisable freely-accessible Socratic AI physics tutor
Eugenio Tufino, Bor Gregorcic
https://arxiv.org/abs/2507.05795 https://arxiv.org/pdf/25…

Creating a customisable freely-accessible Socratic AI physics tutor
This paper explores role engineering as an effective paradigm for customizing Large Language Models (LLMs) into specialized AI tutors for physics education. We demonstrate this methodology by designing a Socratic physics problem-solving tutor using Google's Gemini Gems feature, defining its pedagogical behavior through a detailed 'script' that specifies its role and persona. We present two illustrative use cases: the first demonstrates the Gem's multimodal ability to analyze a student's hand-dr…

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
Abdelaziz Salama, Zeinab Nezami, Mohammed M. H. Qazzaz, Maryam Hafeez, Syed Ali Raza Zaidi
https://arxiv.org/abs/2507.21696

Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN
The deployment of AI agents within legacy Radio Access Network (RAN) infrastructure poses significant safety and reliability challenges for future 6G networks. This paper presents a novel Edge AI framework for autonomous network optimisation in Open RAN environments, addressing these challenges through three core innovations: (1) a persona-based multi-tools architecture enabling distributed, context-aware decision-making; (2) proactive anomaly detection agent powered by traffic predictive tool;…

Nadie se hace la persona mšs rica del mundo honradamente.

Leveraging LLMs for Persona-Based Visualization of Election Data
Swaroop Panda, Arun Kumar Sekar
https://arxiv.org/abs/2507.21900 https://arxiv.org/pdf/250…

Leveraging LLMs for Persona-Based Visualization of Election Data
Visualizations are essential tools for disseminating information regarding elections and their outcomes, potentially influencing public perceptions. Personas, delineating distinctive segments within the populace, furnish a valuable framework for comprehending the nuanced perspectives, requisites, and behaviors of diverse voter demographics. In this work, we propose making visualizations tailored to these personas to make election information easier to understand and more relevant. Using data fr…

Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents
Sarah Mercer, Daniel P. Martin, Phil Swatton
https://arxiv.org/abs/2508.00742

Applying Psychometrics to Large Language Model Simulated Populations: Recreating the HEXACO Personality Inventory Experiment with Generative Agents
Generative agents powered by Large Language Models demonstrate human-like characteristics through sophisticated natural language interactions. Their ability to assume roles and personalities based on predefined character biographies has positioned them as cost-effective substitutes for human participants in social science research. This paper explores the validity of such persona-based agents in representing human populations; we recreate the HEXACO personality inventory experiment by surveying…

Relacionado con lo que acabo de retootear.
Hace un año una persona de la familia me enseñó una canción que había creado una IA apartir de un poema que había escrito. La música era la que habría compuesto alguien que se conoce la escala mayor de Do y los acordes mayores. No había una progresión mínimamente trabajada, no eran mšs que una sucesión de acordes muy simples uno tras otro tras otro sin mšs.

🇺🇦 #NowPlaying on KEXP's #AfternoonShow
Tyler, The Creator:
🎵 Sucka Free
#Tyler #TheCreator
https://reyrzy.bandcamp.com/track/sucka-free-love-tyler-the-creator-x-persona-4-mashup
https://open.spotify.com/track/7DIMKlmJ0CL6eROkbptoqi

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
Jiaju Chen, Yuxuan Lu, Xiaojie Wang, Huimin Zeng, Jing Huang, Jiri Gesi, Ying Xu, Bingsheng Yao, Dakuo Wang
https://arxiv.org/abs/2507.21028

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation
Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily de…

This https://arxiv.org/abs/2412.04629 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates
Large language models (LLMs) are enabling designers to give life to exciting new user experiences for information access. In this work, we present a system that generates LLM personas to debate a topic of interest from different perspectives. How might information seekers use and benefit from such a system? Can centering information access around diverse viewpoints help to mitigate thorny challenges like confirmation bias in which information seekers over-trust search results matching existing …

🇺🇦 #NowPlaying on KEXP's #VarietyMix
Tyler, The Creator:
🎵 Sucka Free
#Tyler #TheCreator
#newRelease 🆕 album
https://reyrzy.bandcamp.com/track/sucka-free-love-tyler-the-creator-x-persona-4-mashup
https://open.spotify.com/track/7DIMKlmJ0CL6eROkbptoqi