Automated Benchmark Auditing for AI Agents and Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Junlin, Bianchi, Federico, Zhu, Shang, Nie, Fan, Kwon, Yongchan, Dhingra, Bhuwan, Zou, James
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications
di: Wang, Junlin, et al.
Pubblicazione: (2024)

To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis
di: Bianchi, Federico, et al.
Pubblicazione: (2025)

ChatShop: Interactive Information Seeking with Language Agents
di: Chen, Sanxing, et al.
Pubblicazione: (2024)

Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
di: Wang, Junlin, et al.
Pubblicazione: (2025)

Adversarial Math Word Problem Generation
di: Xie, Roy, et al.
Pubblicazione: (2024)

Atomic Consistency Preference Optimization for Long-Form Question Answering
di: Chen, Jingfeng, et al.
Pubblicazione: (2025)

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
di: Huang, Yukun, et al.
Pubblicazione: (2024)

GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings
di: Thirukovalluru, Raghuveer, et al.
Pubblicazione: (2024)

Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
di: Bianchi, Federico, et al.
Pubblicazione: (2024)

Mixture-of-Agents Enhances Large Language Model Capabilities
di: Wang, Junlin, et al.
Pubblicazione: (2024)

Calibrating Long-form Generations from Large Language Models
di: Huang, Yukun, et al.
Pubblicazione: (2024)

Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation
di: Periasami, Ajay Vikram, et al.
Pubblicazione: (2026)

Coding Agents are Effective Long-Context Processors
di: Cao, Weili, et al.
Pubblicazione: (2026)

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
di: Huang, Yukun, et al.
Pubblicazione: (2025)

Atomic Self-Consistency for Better Long Form Generations
di: Thirukovalluru, Raghuveer, et al.
Pubblicazione: (2024)

ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
di: Kwon, Yongchan, et al.
Pubblicazione: (2025)

DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
di: Nie, Fan, et al.
Pubblicazione: (2026)

Interleaved Reasoning for Large Language Models via Reinforcement Learning
di: Xie, Roy, et al.
Pubblicazione: (2025)

Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
di: Xie, Roy, et al.
Pubblicazione: (2025)

RVPO: Risk-Sensitive Alignment via Variance Regularization
di: Montero, Ivan, et al.
Pubblicazione: (2026)

Real-time Factuality Assessment from Adversarial Feedback
di: Chen, Sanxing, et al.
Pubblicazione: (2024)

Hierarchical Multi-Label Classification of Online Vaccine Concerns
di: Zhu, Chloe Qinyu, et al.
Pubblicazione: (2024)

Extracting Polymer Nanocomposite Samples from Full-Length Documents
di: Khalighinejad, Ghazal, et al.
Pubblicazione: (2024)

IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
di: Fu, Deqing, et al.
Pubblicazione: (2024)

Evaluating Morphological Compositional Generalization in Large Language Models
di: Ismayilzada, Mete, et al.
Pubblicazione: (2024)

ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods
di: Xie, Roy, et al.
Pubblicazione: (2024)

A Platform for Investigating Public Health Content with Efficient Concern Classification
di: Li, Christopher, et al.
Pubblicazione: (2025)

InData: Towards Secure Multi-Step, Tool-Based Data Analysis
di: K, Karthikeyan, et al.
Pubblicazione: (2025)

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
di: Tu, Xinming, et al.
Pubblicazione: (2026)

Document-as-Image Representations Fall Short for Scientific Retrieval
di: Khalighinejad, Ghazal, et al.
Pubblicazione: (2026)

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
di: Bianchi, Federico, et al.
Pubblicazione: (2023)

OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
di: Wang, Zilong, et al.
Pubblicazione: (2024)

AuditWen:An Open-Source Large Language Model for Audit
di: Huang, Jiajia, et al.
Pubblicazione: (2024)

Benchmarking Linguistic Diversity of Large Language Models
di: Guo, Yanzhu, et al.
Pubblicazione: (2024)

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
di: Chen, Sanxing, et al.
Pubblicazione: (2025)

Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
di: Chun, Yongchan, et al.
Pubblicazione: (2025)

Benchmarking Gaslighting Attacks Against Speech Large Language Models
di: Wu, Jinyang, et al.
Pubblicazione: (2025)

"Sorry, I Didn't Catch That": How Speech Models Miss What Matters Most
di: Zhou, Kaitlyn, et al.
Pubblicazione: (2026)

ReliableMath: Benchmark of Reliable Mathematical Reasoning on Large Language Models
di: Xue, Boyang, et al.
Pubblicazione: (2025)

Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
di: Berger, Armin, et al.
Pubblicazione: (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	"it"
VUFIND_SESSION	"f10c210fd8ec5bb23b168695dd64cef6"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790894924.0505 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "f10c210fd8ec5bb23b168695dd64cef6" ]`]
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=it; VUFIND_SESSION=f10c210fd8ec5bb23b168695dd64cef6; 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	"216.73.217.142"
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	"20478"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_26079/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_26079/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790894924.0463
REQUEST_TIME	1790894924

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler