Improving Cross-Cultural Survey Simulation with Calibrated Value Personas

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Abels, Axel, Domingos, Elias Fernandez, Shah, Apurva, Lenaerts, Tom
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds
di: Abels, Axel, et al.
Pubblicazione: (2025)

Artificial Delegates Resolve Fairness Issues in Perpetual Voting with Partial Turnout
di: Shah, Apurva, et al.
Pubblicazione: (2025)

Mitigating Biases in Collective Decision-Making: Enhancing Performance in the Face of Fake News
di: Abels, Axel, et al.
Pubblicazione: (2024)

Defaults: a double-edged sword in governing common resources
di: Montero-Porras, Eladio, et al.
Pubblicazione: (2024)

Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
di: Liu, Haijiang, et al.
Pubblicazione: (2025)

Quantifying the Persona Effect in LLM Simulations
di: Hu, Tiancheng, et al.
Pubblicazione: (2024)

Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
di: Greco, Candida M., et al.
Pubblicazione: (2026)

German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
di: Rupprecht, Jens, et al.
Pubblicazione: (2025)

Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency
di: Batzner, Jan, et al.
Pubblicazione: (2025)

The Need for a Socially-Grounded Persona Framework for User Simulation
di: Venkit, Pranav Narayanan, et al.
Pubblicazione: (2026)

Cultural Value Differences of LLMs: Prompt, Language, and Model Size
di: Zhong, Qishuai, et al.
Pubblicazione: (2024)

Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
di: Kiet, Huynh Trung, et al.
Pubblicazione: (2026)

On The Conceptualization and Societal Impact of Cross-Cultural Bias
di: Bhandari, Vitthal
Pubblicazione: (2025)

WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models
di: Zhao, Wenlong, et al.
Pubblicazione: (2024)

Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health
di: Dey, Sumon Kanti, et al.
Pubblicazione: (2025)

When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models
di: Venkata, Pruthvinath Jeripity
Pubblicazione: (2026)

Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need
di: Bai, Yuqi, et al.
Pubblicazione: (2025)

Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?
di: Tzachristas, Ioannis, et al.
Pubblicazione: (2025)

Misalignment of LLM-Generated Personas with Human Perceptions in Low-Resource Settings
di: Prama, Tabia Tanzin, et al.
Pubblicazione: (2025)

Towards Measuring and Modeling "Culture" in LLMs: A Survey
di: Adilazuarda, Muhammad Farid, et al.
Pubblicazione: (2024)

Language-based Valence and Arousal Expressions between the United States and China: a Cross-Cultural Examination
di: Cho, Young-Min, et al.
Pubblicazione: (2024)

Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs
di: Sakai, Shintaro, et al.
Pubblicazione: (2025)

Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection
di: Gajewska, Ewelina, et al.
Pubblicazione: (2025)

From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
di: Mou, Xinyi, et al.
Pubblicazione: (2024)

LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations
di: Solopova, Veronika, et al.
Pubblicazione: (2026)

Culture is Not Trivia: Sociocultural Theory for Cultural NLP
di: Zhou, Naitian, et al.
Pubblicazione: (2025)

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
di: Lee, Jaehyeok, et al.
Pubblicazione: (2026)

Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness
di: Feroz, Faisal, et al.
Pubblicazione: (2026)

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs
di: de Landa, Joseba Fernandez, et al.
Pubblicazione: (2026)

LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans
di: Bojic, Ljubisa, et al.
Pubblicazione: (2026)

Are Vision Language Models Cross-Cultural Theory of Mind Reasoners?
di: Nazi, Zabir Al, et al.
Pubblicazione: (2025)

Voice Under Revision: Large Language Models and the Normalization of Personal Narrative
di: van Nuenen, Tom
Pubblicazione: (2026)

Recognition Without Authorization: LLMs and the Moral Order of Online Advice
di: van Nuenen, Tom
Pubblicazione: (2026)

Embracing Dialectic Intersubjectivity: Coordination of Different Perspectives in Content Analysis with LLM Persona Simulation
di: Kang, Taewoo, et al.
Pubblicazione: (2025)

Steering at the Source: Style Modulation Heads for Robust Persona Control
di: Izawa, Yoshihiro, et al.
Pubblicazione: (2026)

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment
di: Kim, Jiseon, et al.
Pubblicazione: (2025)

When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment
di: Ferrer, Robinson, et al.
Pubblicazione: (2026)

SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation
di: Fan, Grace Jiarui, et al.
Pubblicazione: (2026)

Investigating Cultural Alignment of Large Language Models
di: AlKhamissi, Badr, et al.
Pubblicazione: (2024)

On Classification with Large Language Models in Cultural Analytics
di: Bamman, David, et al.
Pubblicazione: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"it"
VUFIND_SESSION	"3e88c2cd9bfc8f370a5e18071c5b4cfc"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790983037.2572 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "3e88c2cd9bfc8f370a5e18071c5b4cfc" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=it; VUFIND_SESSION=3e88c2cd9bfc8f370a5e18071c5b4cfc"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"30702"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_16193/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_16193/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790983037.2528
REQUEST_TIME	1790983037

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler