Contextual Metric Meta-Evaluation by Measuring Local Metric Accuracy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Deviyani, Athiya, Diaz, Fernando
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quantifying the Statistical Effect of Rubric Modifications on Human-Autorater Agreement
por: Huynh, Jessica, et al.
Publicado: (2026)

Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
por: Gur-Arieh, Yoav, et al.
Publicado: (2026)

Meta-Evaluating Local LLMs: Rethinking Performance Metrics for Serious Games
por: Isaza-Giraldo, Andrés, et al.
Publicado: (2025)

A Critical Look at Meta-evaluating Summarisation Evaluation Metrics
por: Dai, Xiang, et al.
Publicado: (2024)

Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies
por: Kocmi, Tom, et al.
Publicado: (2024)

Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics
por: Pauli, Amalie Brogaard, et al.
Publicado: (2025)

Dynamic Meta-Metrics: Source-Sentence Conditioned Weighting for MT Evaluation
por: Zhang, Luke, et al.
Publicado: (2026)

Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!
por: Perrella, Stefano, et al.
Publicado: (2024)

LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation
por: Eigler, Lukáš, et al.
Publicado: (2026)

Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy
por: Thompson, Brian, et al.
Publicado: (2024)

Nonparametric LLM Evaluation from Preference Data
por: Frauen, Dennis, et al.
Publicado: (2026)

MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration
por: Anugraha, David, et al.
Publicado: (2024)

MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
por: Winata, Genta Indra, et al.
Publicado: (2024)

KG-EDAS: A Meta-Metric Framework for Evaluating Knowledge Graph Completion Models
por: Gul, Haji, et al.
Publicado: (2025)

Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation
por: Ramprasad, Sanjana, et al.
Publicado: (2024)

Evaluating Metrics for Bias in Word Embeddings
por: Schröder, Sarah, et al.
Publicado: (2021)

Comparative Experimentation of Accuracy Metrics in Automated Medical Reporting: The Case of Otitis Consultations
por: Faber, Wouter, et al.
Publicado: (2023)

APPLS: Evaluating Evaluation Metrics for Plain Language Summarization
por: Guo, Yue, et al.
Publicado: (2023)

Granular Change Accuracy: A More Accurate Performance Metric for Dialogue State Tracking
por: Aksu, Taha, et al.
Publicado: (2024)

Faithful Model Evaluation for Model-Based Metrics
por: Goyal, Palash, et al.
Publicado: (2023)

Towards Region-aware Bias Evaluation Metrics
por: Borah, Angana, et al.
Publicado: (2024)

CASPR: Automated Evaluation Metric for Contrastive Summarization
por: Ananthamurugan, Nirupan, et al.
Publicado: (2024)

An Automatic Quality Metric for Evaluating Simultaneous Interpretation
por: Makinae, Mana, et al.
Publicado: (2024)

Calibrating Model-Based Evaluation Metrics for Summarization
por: Liu, Hongye, et al.
Publicado: (2026)

A Measure of the System Dependence of Automated Metrics
por: von Däniken, Pius, et al.
Publicado: (2024)

Balanced Accuracy: The Right Metric for Evaluating LLM Judges -- Explained through Youden's J statistic
por: Collot, Stephane, et al.
Publicado: (2025)

Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?
por: Mukherjee, Sourabrata, et al.
Publicado: (2025)

Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation
por: Polák, Peter, et al.
Publicado: (2025)

Evaluating Metrics for Safety with LLM-as-Judges
por: Clegg, Kester, et al.
Publicado: (2025)

MetricalARGS: A Taxonomy for Studying Metrical Poetry with LLMs
por: Kranti, Chalamalasetti, et al.
Publicado: (2025)

KIEval: Evaluation Metric for Document Key Information Extraction
por: Khang, Minsoo, et al.
Publicado: (2025)

Identifying Reliable Evaluation Metrics for Scientific Text Revision
por: Jourdan, Léane, et al.
Publicado: (2025)

Hacking Neural Evaluation Metrics with Single Hub Text
por: Deguchi, Hiroyuki, et al.
Publicado: (2025)

Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions
por: Hu, Taojun, et al.
Publicado: (2024)

Evaluating Automatic Metrics with Incremental Machine Translation Systems
por: Wu, Guojun, et al.
Publicado: (2024)

Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
por: Kasaei, Seyed Amir, et al.
Publicado: (2025)

Towards Explainable Evaluation Metrics for Machine Translation
por: Leiter, Christoph, et al.
Publicado: (2023)

Evaluation Metrics for Text Data Augmentation in NLP
por: Amadeus, Marcellus, et al.
Publicado: (2024)

GEMMAS: Graph-based Evaluation Metrics for Multi Agent Systems
por: Lee, Jisoo, et al.
Publicado: (2025)

Reference-free Evaluation Metrics for Text Generation: A Survey
por: Ito, Takumi, et al.
Publicado: (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
ui	"standard"
language	"es"
VUFIND_SESSION	"13d103e73c3f9db994d2fb0343e30fe7"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790836481.5476 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "13d103e73c3f9db994d2fb0343e30fe7" ]`]
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=es; VUFIND_SESSION=13d103e73c3f9db994d2fb0343e30fe7"
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	"46972"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2503_19828/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2503_19828/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790836481.5432
REQUEST_TIME	1790836481

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler