Taming CATS: Controllable Automatic Text Simplification through Instruction Fine-Tuning with Control Tokens

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hubarava, Hanna, Gao, Yingqiang
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

Template-Based Text-to-Image Alignment for Language Accessibility: A Study on Visualizing Text Simplifications
di: Souayed, Belkiss, et al.
Pubblicazione: (2025)

DETECT: Determining Ease and Textual Clarity of German Text Simplifications
di: Korobeynikova, Maria, et al.
Pubblicazione: (2025)

Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities
di: Gao, Yingqiang, et al.
Pubblicazione: (2025)

Controllable Text Generation in the Instruction-Tuning Era
di: Ashok, Dhananjay, et al.
Pubblicazione: (2024)

Readability Measures and Automatic Text Simplification: In the Search of a Construct
di: Cardon, Rémi, et al.
Pubblicazione: (2025)

Language Resources in Spanish for Automatic Text Simplification across Domains
di: Moreno-Sandoval, Antonio, et al.
Pubblicazione: (2024)

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning
di: Gao, Chang, et al.
Pubblicazione: (2023)

Automatic Lexical Simplification for Turkish
di: Uluslu, Ahmet Yavuz
Pubblicazione: (2022)

Automatic Simplification of Common Vulnerabilities and Exposures Descriptions
di: Vehomäki, Varpu, et al.
Pubblicazione: (2026)

Text Simplification with Sentence Embeddings
di: Shardlow, Matthew
Pubblicazione: (2025)

Fine-grained Controllable Text Generation through In-context Learning with Feedback
di: Thillainathan, Sarubi, et al.
Pubblicazione: (2024)

From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning
di: Niu, Zihan, et al.
Pubblicazione: (2026)

Analysing Zero-Shot Readability-Controlled Sentence Simplification
di: Barayan, Abdullah, et al.
Pubblicazione: (2024)

The SAMER Arabic Text Simplification Corpus
di: Alhafni, Bashar, et al.
Pubblicazione: (2024)

Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets
di: Barbu, Eduard, et al.
Pubblicazione: (2025)

A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification
di: Fatemi, Sorouralsadat, et al.
Pubblicazione: (2024)

APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification
di: Chernodub, Artem, et al.
Pubblicazione: (2025)

EASSE-DE: Easier Automatic Sentence Simplification Evaluation for German
di: Stodden, Regina
Pubblicazione: (2024)

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
di: Wang, Xinpeng, et al.
Pubblicazione: (2024)

Role of Dependency Distance in Text Simplification: A Human vs ChatGPT Simplification Comparison
di: Lee, Sumi, et al.
Pubblicazione: (2024)

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
di: Liu, Yilun, et al.
Pubblicazione: (2023)

LiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes
di: Shi, Chufan, et al.
Pubblicazione: (2024)

Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance
di: Alajrami, Ahmed, et al.
Pubblicazione: (2025)

UM_FHS at the CLEF 2025 SimpleText Track: Comparing No-Context and Fine-Tune Approaches for GPT-4.1 Models in Sentence and Document-Level Text Simplification
di: Kocbek, Primoz, et al.
Pubblicazione: (2025)

Personalized Text Generation with Fine-Grained Linguistic Control
di: Alhafni, Bashar, et al.
Pubblicazione: (2024)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
di: Ruan, Zhiwen, et al.
Pubblicazione: (2026)

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning
di: Du, Yanrui, et al.
Pubblicazione: (2024)

SiTSE: Sinhala Text Simplification Dataset and Evaluation
di: Ranathunga, Surangika, et al.
Pubblicazione: (2024)

Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
di: Yousefiramandi, Amirhossein, et al.
Pubblicazione: (2025)

JEBS: A Fine-grained Biomedical Lexical Simplification Task
di: Xia, William, et al.
Pubblicazione: (2025)

Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation
di: Yang, Jianjiang, et al.
Pubblicazione: (2025)

RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
di: Yang, Yixin, et al.
Pubblicazione: (2025)

ToDi: Token-wise Distillation via Fine-Grained Divergence Control
di: Jung, Seongryong, et al.
Pubblicazione: (2025)

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
di: Jindal, Ishan, et al.
Pubblicazione: (2024)

Spivavtor: An Instruction Tuned Ukrainian Text Editing Model
di: Saini, Aman, et al.
Pubblicazione: (2024)

DELIFT: Data Efficient Language model Instruction Fine Tuning
di: Agarwal, Ishika, et al.
Pubblicazione: (2024)

ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation
di: Stahl, Maja, et al.
Pubblicazione: (2025)

Dynamics of Instruction Fine-Tuning for Chinese Large Language Models
di: Song, Chiyu, et al.
Pubblicazione: (2023)

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
di: Feng, Weitao, et al.
Pubblicazione: (2025)

Evaluating LLMs for Targeted Concept Simplification for Domain-Specific Texts
di: Asthana, Sumit, 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
VUFIND_SESSION	"b234f20e6498436b5ec04bbada9a12e5"
ui	"standard"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790863274.9987 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b234f20e6498436b5ec04bbada9a12e5" ]`]
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=b234f20e6498436b5ec04bbada9a12e5; ui=standard; language=it"
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	"28514"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2604_01779/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_01779/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790863274.9824
REQUEST_TIME	1790863274

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler