Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kogan, David, Nguyen, Sam, Suzuki, Masanori, Chen, Feiyang
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

Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications
di: Kogan, David, et al.
Pubblicazione: (2025)

A Survey on Prompting Techniques in LLMs
di: Bhandari, Prabin
Pubblicazione: (2023)

Enhanced Detection of Conversational Mental Manipulation Through Advanced Prompting Techniques
di: Yang, Ivory, et al.
Pubblicazione: (2024)

Prompting LLMs: Length Control for Isometric Machine Translation
di: Javorský, Dávid, et al.
Pubblicazione: (2025)

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
di: Zhang, Xinghua, et al.
Pubblicazione: (2024)

A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis
di: Imajo, Kentaro, et al.
Pubblicazione: (2025)

Selective Prompting Tuning for Personalized Conversations with LLMs
di: Huang, Qiushi, et al.
Pubblicazione: (2024)

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
di: Chen, Si, et al.
Pubblicazione: (2024)

Conversational Prompt Engineering
di: Ein-Dor, Liat, et al.
Pubblicazione: (2024)

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
di: Pan, Haowen, et al.
Pubblicazione: (2025)

Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs
di: Xie, Juncheng, et al.
Pubblicazione: (2025)

Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs
di: Naderi, Nariman, et al.
Pubblicazione: (2025)

Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes
di: Kamruzzaman, Mahammed, et al.
Pubblicazione: (2024)

Prompt Highlighter: Interactive Control for Multi-Modal LLMs
di: Zhang, Yuechen, et al.
Pubblicazione: (2023)

Detecting Conversational Mental Manipulation with Intent-Aware Prompting
di: Ma, Jiayuan, et al.
Pubblicazione: (2024)

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
di: Zhang, Jun, et al.
Pubblicazione: (2026)

Spot the bot: Coarse-Grained Partition of Semantic Paths for Bots and Humans
di: Gromov, Vasilii A., et al.
Pubblicazione: (2024)

Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs
di: Chen, Yingjian, et al.
Pubblicazione: (2025)

Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs
di: Heris, Mostapha Kalami
Pubblicazione: (2025)

Construction of a Japanese Financial Benchmark for Large Language Models
di: Hirano, Masanori
Pubblicazione: (2024)

How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?
di: Zhu, Xiliang, et al.
Pubblicazione: (2025)

The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging
di: Hirano, Masanori, et al.
Pubblicazione: (2024)

ART: Attention Replacement Technique to Improve Factuality in LLMs
di: Luo, Ziqin, et al.
Pubblicazione: (2026)

Scaling Personality Control in LLMs with Big Five Scaler Prompts
di: Cho, Gunhee, et al.
Pubblicazione: (2025)

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
di: Lu, Haiquan, et al.
Pubblicazione: (2026)

Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques
di: Koorndijk, Jeanice
Pubblicazione: (2025)

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
di: Zhuo, Jingming, et al.
Pubblicazione: (2024)

Prompt-MII: Meta-Learning Instruction Induction for LLMs
di: Xiao, Emily, et al.
Pubblicazione: (2025)

Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
di: Castillo-Bolado, David, et al.
Pubblicazione: (2024)

Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
di: Thulke, David, et al.
Pubblicazione: (2024)

The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
di: Schulhoff, Sander, et al.
Pubblicazione: (2024)

Automatic Prompt Generation via Adaptive Selection of Prompting Techniques
di: Ikenoue, Yohei, et al.
Pubblicazione: (2025)

Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis
di: Gao, Zhiqiang, et al.
Pubblicazione: (2025)

Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
di: Chen, Tianlang, et al.
Pubblicazione: (2026)

The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts
di: Haijima, Wakana, et al.
Pubblicazione: (2024)

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning
di: Li, Feiyang, et al.
Pubblicazione: (2026)

SpecPL: Disentangling Spectral Granularity for Prompt Learning
di: Zhou, Jingtao, et al.
Pubblicazione: (2026)

Reproducing the Metric-Based Evaluation of a Set of Controllable Text Generation Techniques
di: Lorandi, Michela, et al.
Pubblicazione: (2024)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
di: Le, Chenqian, et al.
Pubblicazione: (2025)

Rhea: Role-aware Heuristic Episodic Attention for Conversational LLMs
di: Hong, Wanyang, 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
ui	"standard"
language	"it"
VUFIND_SESSION	"7b5606aa30701236467c56e3477ff155"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790970663.9052 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "7b5606aa30701236467c56e3477ff155" ]`]
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=it; VUFIND_SESSION=7b5606aa30701236467c56e3477ff155"
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	"2090"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2603_03317/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2603_03317/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790970663.9005
REQUEST_TIME	1790970663

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler