Tutoring Large Language Models to be Domain-adaptive, Precise, and Safe

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Banerjee, Somnath
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
par: Hazra, Rima, et autres
Publié: (2026)

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
par: Banerjee, Somnath, et autres
Publié: (2024)

AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails
par: Chowdhury, Sankalan Pal, et autres
Publié: (2024)

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
par: Adak, Sayantan, et autres
Publié: (2025)

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
par: Hazra, Rima, et autres
Publié: (2024)

Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
par: Banerjee, Somnath, et autres
Publié: (2026)

SafeMath: Inference-time Safety improves Math Accuracy
par: Basu, Sagnik, et autres
Publié: (2026)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
par: Hazra, Rima, et autres
Publié: (2024)

Language Models as Science Tutors
par: Chevalier, Alexis, et autres
Publié: (2024)

Empowering Private Tutoring by Chaining Large Language Models
par: Chen, Yulin, et autres
Publié: (2023)

Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations
par: Banerjee, Somnath, et autres
Publié: (2025)

AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models
par: Belay, Tadesse Destaw, et autres
Publié: (2026)

ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models
par: Banerjee, Somnath, et autres
Publié: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
par: Cao, Chuxue, et autres
Publié: (2025)

Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study
par: Borchers, Conrad, et autres
Publié: (2025)

PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors
par: Rooein, Donya, et autres
Publié: (2026)

Exploring Applications of Transfer-State Large Language Models: Cognitive Profiling and Socratic AI Tutoring
par: Noguchi, Minori
Publié: (2026)

Toward Automated Qualitative Analysis: Leveraging Large Language Models for Tutoring Dialogue Evaluation
par: Gu, Megan, et autres
Publié: (2025)

Analyzing Sentiment Polarity Reduction in News Presentation through Contextual Perturbation and Large Language Models
par: Kuila, Alapan, et autres
Publié: (2024)

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
par: Cui, Chenhang, et autres
Publié: (2024)

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
par: Banerjee, Somnath, et autres
Publié: (2024)

Large Language Models Approach Expert Pedagogical Quality in Math Tutoring but Differ in Instructional and Linguistic Profiles
par: Abdulsalam, Ramatu Oiza, et autres
Publié: (2025)

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
par: Banerjee, Somnath, et autres
Publié: (2025)

Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
par: Banerjee, Somnath, et autres
Publié: (2026)

Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System
par: Schmucker, Robin, et autres
Publié: (2024)

Ensembling Large Language Models to Characterize Affective Dynamics in Student-AI Tutor Dialogues
par: Zhang, Chenyu, et autres
Publié: (2025)

Precise In-Parameter Concept Erasure in Large Language Models
par: Gur-Arieh, Yoav, et autres
Publié: (2025)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
par: Daheim, Nico, et autres
Publié: (2024)

Developing Safe and Responsible Large Language Model : Can We Balance Bias Reduction and Language Understanding in Large Language Models?
par: Raza, Shaina, et autres
Publié: (2024)

SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance
par: Walker, Connor, et autres
Publié: (2024)

ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
par: Zhang, Hengxiang, et autres
Publié: (2024)

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
par: Zhang, Xiaoyun, et autres
Publié: (2024)

Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
par: Huang, Jen-tse, et autres
Publié: (2026)

Exploring Safety-Utility Trade-Offs in Personalized Language Models
par: Vijjini, Anvesh Rao, et autres
Publié: (2024)

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
par: Banerjee, Somnath, et autres
Publié: (2024)

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
par: Lee, Seanie, et autres
Publié: (2025)

Precise Length Control in Large Language Models
par: Butcher, Bradley, et autres
Publié: (2024)

Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language
par: Zhukova, Anastasia, et autres
Publié: (2025)

InfFeed: Influence Functions as a Feedback to Improve the Performance of Subjective Tasks
par: Banerjee, Somnath, et autres
Publié: (2024)

DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem
par: Banerjee, Somnath, 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
language	"fr"
VUFIND_SESSION	"c046ea49ecb9f06d05e24a94f8b49925"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790987131.841 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c046ea49ecb9f06d05e24a94f8b49925" ]`]
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=fr; VUFIND_SESSION=c046ea49ecb9f06d05e24a94f8b49925; 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	"63196"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2602_13860/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2602_13860/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790987131.8365
REQUEST_TIME	1790987131

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler