Applied Explainability for Large Language Models: A Comparative Study

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Kancharla, Venkata Abhinandan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Machine Learning I.2.7; I.5.1
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models
par: Dhole, Kaustubh D.
Publié: (2025)

Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
par: Yocam, Eric, et autres
Publié: (2026)

Efficient Strategy for Improving Large Language Model (LLM) Capabilities
par: Gutiérrez, Julián Camilo Velandia
Publié: (2025)

A Lightweight Approach to Detection of AI-Generated Texts Using Stylometric Features
par: Aityan, Sergey K., et autres
Publié: (2025)

Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory
par: Cacioli, Jon-Paul
Publié: (2026)

Large Language Models Are Not Strong Abstract Reasoners
par: Gendron, Gaël, et autres
Publié: (2023)

ADALog: Adaptive Unsupervised Anomaly detection in Logs with Self-attention Masked Language Model
par: Pospieszny, Przemek, et autres
Publié: (2025)

Classification of descriptions and summary using multiple passes of statistical and natural language toolkits
par: Banthia, Saumya, et autres
Publié: (2020)

Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization
par: Wen, Yuqiao, et autres
Publié: (2025)

A Semantic Approach to Negation Detection and Word Disambiguation with Natural Language Processing
par: Okpala, Izunna, et autres
Publié: (2023)

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
par: Reddy, Sandeep, et autres
Publié: (2025)

When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD
par: Mandal, Paul K.
Publié: (2025)

EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation
par: Wen, Yuqiao, et autres
Publié: (2024)

Less is More: Learning Graph Tasks with Just LLMs
par: Shirai, Sola, et autres
Publié: (2025)

Adversarially Probing Cross-Family Sound Symbolism in 27 Languages
par: Sharma, Anika, et autres
Publié: (2025)

MIMIC-SR-ICD11: A Dataset for Narrative-Based Diagnosis
par: Wu, Yuexin, et autres
Publié: (2025)

DROID: Dual Representation for Out-of-Scope Intent Detection
par: Rashwan, Wael, et autres
Publié: (2025)

Transparent but Powerful: Explainability, Accuracy, and Generalizability in ADHD Detection from Social Media Data
par: Wiechmann, D., et autres
Publié: (2024)

Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
par: Abusaqer, Mahmoud, et autres
Publié: (2025)

Accelerating Language Model Workflows with Prompt Choreography
par: Bai, TJ, et autres
Publié: (2025)

Cost-Aware Model Selection for Text Classification: Multi-Objective Trade-offs Between Fine-Tuned Encoders and LLM Prompting in Production
par: Gonzalez, Alberto Andres Valdes
Publié: (2026)

Measuring Intent Comprehension in LLMs
par: Kunievsky, Nadav, et autres
Publié: (2025)

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
par: Nauen, Tobias Christian, et autres
Publié: (2024)

Correspondence of high-dimensional emotion structures elicited by video clips between humans and Multimodal LLMs
par: Asanuma, Haruka, et autres
Publié: (2025)

Suicide Risk Assessment Using Multimodal Speech Features: A Study on the SW1 Challenge Dataset
par: Marie, Ambre, et autres
Publié: (2025)

Listwise Direct Preference Optimization with Multi-Dimensional Preference Mixing
par: Sun, Yuhui, et autres
Publié: (2025)

Predicting When to Trust Vision-Language Models for Spatial Reasoning
par: Imran, Muhammad, et autres
Publié: (2026)

GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping
par: Wen, Qifu, et autres
Publié: (2025)

Let Your Graph Do the Talking: Encoding Structured Data for LLMs
par: Perozzi, Bryan, et autres
Publié: (2024)

FinBERT-QA: Financial Question Answering with pre-trained BERT Language Models
par: Yuan, Bithiah
Publié: (2025)

A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction
par: Bogachov, Bogdan, et autres
Publié: (2025)

Beyond Subtokens: A Rich Character Embedding for Low-resource and Morphologically Complex Languages
par: Schneider, Felix, et autres
Publié: (2026)

Emotional Voice Messages (EMOVOME) database: emotion recognition in spontaneous voice messages
par: Zaragozá, Lucía Gómez, et autres
Publié: (2024)

Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content
par: Koushik, Girish A., et autres
Publié: (2025)

A Comparative Study of Feature Selection in Tsetlin Machines
par: Halenka, Vojtech, et autres
Publié: (2025)

Large Language Model (LLM) Bias Index -- LLMBI
par: Oketunji, Abiodun Finbarrs, et autres
Publié: (2023)

Logits-Constrained Framework with RoBERTa for Ancient Chinese NER
par: Hua, Wenjie, et autres
Publié: (2025)

LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems
par: Bachar, Or, et autres
Publié: (2026)

Semantic Superiority vs. Forensic Efficiency: A Comparative Analysis of Deep Learning and Psycholinguistics for Business Email Compromise Detection
par: Adjei, Yaw Osei, et autres
Publié: (2025)

The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem
par: Hakim, Joe B, et autres
Publié: (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
VUFIND_SESSION	"e4257bc30115d3e1329f8c8f37de1cec"
ui	"standard"
language	"fr"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790887901.5965 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "e4257bc30115d3e1329f8c8f37de1cec" ]`]
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	"VUFIND_SESSION=e4257bc30115d3e1329f8c8f37de1cec; ui=standard; language=fr"
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	"14401"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2604_15371/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2604_15371/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790887901.5913
REQUEST_TIME	1790887901

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler