Cross-model Control: Improving Multiple Large Language Models in One-time Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Jiayi, Sun, Hao, Cai, Hengyi, Su, Lixin, Wang, Shuaiqiang, Yin, Dawei, Li, Xiang, Gao, Ming
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
di: Wu, Jiayi, et al.
Pubblicazione: (2024)

AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
di: Sun, Hao, et al.
Pubblicazione: (2024)

TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
di: Ni, Hang, et al.
Pubblicazione: (2025)

Tool Learning with Large Language Models: A Survey
di: Qu, Changle, et al.
Pubblicazione: (2024)

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies
di: Ni, Xuanfan, et al.
Pubblicazione: (2024)

Towards Completeness-Oriented Tool Retrieval for Large Language Models
di: Qu, Changle, et al.
Pubblicazione: (2024)

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
di: Sun, Hao, et al.
Pubblicazione: (2023)

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
di: Qu, Changle, et al.
Pubblicazione: (2026)

CoRanking: Collaborative Ranking with Small and Large Ranking Agents
di: Liu, Wenhan, et al.
Pubblicazione: (2025)

Improving the Robustness of Large Language Models via Consistency Alignment
di: Zhao, Yukun, et al.
Pubblicazione: (2024)

AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis
di: Sun, Zexu, et al.
Pubblicazione: (2026)

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
di: Zhu, Junda, et al.
Pubblicazione: (2025)

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching
di: Peng, Jingyu, et al.
Pubblicazione: (2025)

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
di: Qu, Changle, et al.
Pubblicazione: (2024)

RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
di: Chen, Tingyu, et al.
Pubblicazione: (2026)

MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
di: Jia, Pengyue, et al.
Pubblicazione: (2023)

Text-Video Retrieval via Variational Multi-Modal Hypergraph Networks
di: Li, Qian, et al.
Pubblicazione: (2024)

Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search
di: Wang, Mingyue, et al.
Pubblicazione: (2026)

Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
di: Sun, Weiwei, et al.
Pubblicazione: (2023)

Behavior-Equivalent Token: Single-Token Replacement for Long Prompts in LLMs
di: Dong, Jiancheng, et al.
Pubblicazione: (2025)

Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language Models
di: Liu, Wenhan, et al.
Pubblicazione: (2024)

Leveraging Generative Models for Real-Time Query-Driven Text Summarization in Large-Scale Web Search
di: Xiong, Zeyu, et al.
Pubblicazione: (2025)

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
di: Wu, Hui, et al.
Pubblicazione: (2026)

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
di: Shi, Zhengliang, et al.
Pubblicazione: (2025)

GraphGPT: Graph Instruction Tuning for Large Language Models
di: Tang, Jiabin, et al.
Pubblicazione: (2023)

DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models
di: Li, Zihao, et al.
Pubblicazione: (2025)

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
di: Wu, Jiulong, et al.
Pubblicazione: (2025)

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
di: Gao, Heyang, et al.
Pubblicazione: (2025)

FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding
di: Deng, Jingyang, et al.
Pubblicazione: (2024)

Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
di: Wei, Wenda, et al.
Pubblicazione: (2025)

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
di: Chen, Yiqun, et al.
Pubblicazione: (2025)

Measuring Maximum Activations in Open Large Language Models
di: Chen, Luxuan, et al.
Pubblicazione: (2026)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
di: Lyu, Yougang, et al.
Pubblicazione: (2024)

Towards AI Search Paradigm
di: Li, Yuchen, et al.
Pubblicazione: (2025)

JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
di: Liu, Fan, et al.
Pubblicazione: (2024)

How to Utilize Complementary Vision-Text Information for 2D Structure Understanding
di: Dong, Jiancheng, et al.
Pubblicazione: (2026)

GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication
di: Tang, Hua, et al.
Pubblicazione: (2025)

SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents
di: Li, Dawei, et al.
Pubblicazione: (2024)

Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization
di: Amin, Hasan, et al.
Pubblicazione: (2026)

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models
di: Zhang, Jiayi, 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"
VUFIND_SESSION	"b7e8b9addcb305bed95cae888fd4898f"
language	"it"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790888846.7483 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b7e8b9addcb305bed95cae888fd4898f" ]`]
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; VUFIND_SESSION=b7e8b9addcb305bed95cae888fd4898f; 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	"216.73.217.142"
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	"60728"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_17599/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_17599/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790888846.7437
REQUEST_TIME	1790888846

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler