Can LLMs faithfully generate their layperson-understandable 'self'?: A Case Study in High-Stakes Domains

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Das, Arion, Mishra, Asutosh, Patel, Amitesh, De, Soumilya, Gurucharan, V., Ghosh, Kripabandhu
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Human-Computer Interaction Machine Learning I.2.7
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
von: Chauhan, Anay, et al.
Veröffentlicht: (2026)

Human Agency, Causality, and the Human Computer Interface in High-Stakes Artificial Intelligence
von: Hattab, Georges
Veröffentlicht: (2026)

Can LLMs and humans be friends? Uncovering factors affecting human-AI intimacy formation
von: Hong, Yeseon, et al.
Veröffentlicht: (2025)

LLAMADRS: Evaluating Open-Source LLMs on Real Clinical Interviews--To Reason or Not to Reason?
von: Kebe, Gaoussou Youssouf, et al.
Veröffentlicht: (2025)

Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation
von: Jin, Meiqing, et al.
Veröffentlicht: (2025)

ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering
von: Ghosh, Shubhra, et al.
Veröffentlicht: (2025)

Functional Flexibility in Generative AI Interfaces: Text Editing with LLMs through Conversations, Toolbars, and Prompts
von: Lehmann, Florian, et al.
Veröffentlicht: (2024)

MemPal: Leveraging Multimodal AI and LLMs for Voice-Activated Object Retrieval in Homes of Older Adults
von: Maniar, Natasha, et al.
Veröffentlicht: (2025)

LLMs Aren't Human: A Critical Perspective on LLM Personality
von: Zierahn, Kim, et al.
Veröffentlicht: (2026)

"The Data Says Otherwise"-Towards Automated Fact-checking and Communication of Data Claims
von: Fu, Yu, et al.
Veröffentlicht: (2024)

Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis
von: Kirk, James R., et al.
Veröffentlicht: (2023)

Helping Johnny Make Sense of Privacy Policies with LLMs
von: Freiberger, Vincent, et al.
Veröffentlicht: (2025)

Therapy as an NLP Task: Psychologists' Comparison of LLMs and Human Peers in CBT
von: Iftikhar, Zainab, et al.
Veröffentlicht: (2024)

"Girl, I'm so Serious": CARE, a Capability Framework for Reproductive Equity in Human-AI Interaction
von: Zhong, Alice, et al.
Veröffentlicht: (2026)

Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
von: He, Shengtao
Veröffentlicht: (2024)

Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities
von: Krishna, Avinash, et al.
Veröffentlicht: (2026)

Visualization of Unstructured Sports Data -- An Example of Cricket Short Text Commentary
von: Behera, Swarup Ranjan, et al.
Veröffentlicht: (2024)

Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant
von: Matveyenko, Joseph, et al.
Veröffentlicht: (2025)

MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems
von: Jing, Haifeng, et al.
Veröffentlicht: (2025)

Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality
von: Freiberger, Vincent, et al.
Veröffentlicht: (2026)

Semantic Decomposition and Selective Context Filtering -- Text Processing Techniques for Context-Aware NLP-Based Systems
von: Villardar, Karl John
Veröffentlicht: (2025)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
von: Saji, Alan, et al.
Veröffentlicht: (2025)

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
von: Khanna, Danush, et al.
Veröffentlicht: (2025)

SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use
von: Patel, Hitesh Laxmichand, et al.
Veröffentlicht: (2025)

Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts
von: Kryshtal, Andrii
Veröffentlicht: (2026)

LLMs and people both learn to form conventions -- just not with each other
von: Jones, Cameron R., et al.
Veröffentlicht: (2026)

CueTip: An Interactive and Explainable Physics-aware Pool Assistant
von: Memery, Sean, et al.
Veröffentlicht: (2025)

Humanizing AI Grading: Student-Centered Insights on Fairness, Trust, Consistency and Transparency
von: Riahi, Bahare, et al.
Veröffentlicht: (2026)

Discovering High Level Patterns from Simulation Traces
von: Memery, Sean, et al.
Veröffentlicht: (2026)

The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making
von: Chun, Jon, et al.
Veröffentlicht: (2026)

FathomGPT: A Natural Language Interface for Interactively Exploring Ocean Science Data
von: Khanal, Nabin, et al.
Veröffentlicht: (2024)

VeriPlan: Integrating Formal Verification and LLMs into End-User Planning
von: Lee, Christine, et al.
Veröffentlicht: (2025)

Elemental Alchemist: A Generative Interface for Semantic Control of Particle Systems Across Dynamic Levels of Abstraction
von: Monteiro, Kyzyl, et al.
Veröffentlicht: (2026)

CommentScope: A Comment-Embedded Assisted Reading System for a Long Text
von: Chen, Shuai, et al.
Veröffentlicht: (2025)

Towards Inclusive Video Commenting: Introducing Signmaku for the Deaf and Hard-of-Hearing
von: Chen, Si, et al.
Veröffentlicht: (2024)

StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes
von: Lehmann, Florian, et al.
Veröffentlicht: (2025)

Remember Me, Not Save Me: A Collective Memory System for Evolving Virtual Identities in Augmented Reality
von: Yu, Tongzhou, et al.
Veröffentlicht: (2026)

Trusting the Search: Unraveling Human Trust in Health Information from Google and ChatGPT
von: Sun, Xin, et al.
Veröffentlicht: (2024)

An AI-powered Public Health Automated Kiosk System for Personalized Care: An Experimental Pilot Study
von: Falahati, Sonya, et al.
Veröffentlicht: (2025)

A Notification Based Nudge for Handling Excessive Smartphone Use
von: Sarker, Partha, et al.
Veröffentlicht: (2025)

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
language	"de"
VUFIND_SESSION	"bac4f3a1d051df90ba1d113eb6f8e37c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790829825.744 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "bac4f3a1d051df90ba1d113eb6f8e37c" ]`]
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	"language=de; VUFIND_SESSION=bac4f3a1d051df90ba1d113eb6f8e37c; ui=standard"
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	"216.73.216.147"
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	"3740"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2412_07781/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2412_07781/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790829825.7395
REQUEST_TIME	1790829825

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler