ShiZhi: A Chinese Lightweight Large Language Model for Court View Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hou, Zhitian, Zeng, Kun
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Exploring Lightweight Large Language Models for Court View Generation
por: Hou, Zhitian, et al.
Publicado: (2026)

Large Language Models Meet Legal Artificial Intelligence: A Survey
por: Hou, Zhitian, et al.
Publicado: (2025)

Event Grounded Criminal Court View Generation with Cooperative (Large) Language Models
por: Yue, Linan, et al.
Publicado: (2024)

Evaluating the Generation Capabilities of Large Chinese Language Models
por: Zeng, Hui, et al.
Publicado: (2023)

CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns
por: Zhou, Zhenhong, et al.
Publicado: (2026)

A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
por: Zhang, Chenyang, et al.
Publicado: (2024)

ZhiFangDanTai: Fine-tuning Graph-based Retrieval-Augmented Generation Model for Traditional Chinese Medicine Formula
por: Zhang, ZiXuan, et al.
Publicado: (2025)

Enhancing Molecular Property Prediction with Knowledge from Large Language Models
por: Zhou, Peng, et al.
Publicado: (2025)

Kuaiji: the First Chinese Accounting Large Language Model
por: Luo, Jiayuan, et al.
Publicado: (2024)

ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
por: Zhang, Hengxiang, et al.
Publicado: (2024)

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
por: He, Yancheng, et al.
Publicado: (2024)

OmniEduBench: A Comprehensive Chinese Benchmark for Evaluating Large Language Models in Education
por: Zhang, Min, et al.
Publicado: (2025)

RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models
por: Rodriguez, Juan Diego, et al.
Publicado: (2025)

The performances of the Chinese and U.S. Large Language Models on the Topic of Chinese Culture
por: Liu, Feiyan, et al.
Publicado: (2026)

C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
por: Wu, Ping, et al.
Publicado: (2025)

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation
por: Liang, Xun, et al.
Publicado: (2023)

Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation
por: Gendron, Barbara, et al.
Publicado: (2026)

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
por: Lyu, Yuanjie, et al.
Publicado: (2024)

CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Models
por: Liu, June M., et al.
Publicado: (2024)

Towards Training A Chinese Large Language Model for Anesthesiology
por: Wang, Zhonghai, et al.
Publicado: (2024)

A Chinese Dataset for Evaluating the Safeguards in Large Language Models
por: Wang, Yuxia, et al.
Publicado: (2024)

Test-Time Learning for Large Language Models
por: Hu, Jinwu, et al.
Publicado: (2025)

Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models
por: Zhu, Chenyu, et al.
Publicado: (2025)

E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models
por: Hou, Jinchang, et al.
Publicado: (2024)

Chumor 1.0: A Truly Funny and Challenging Chinese Humor Understanding Dataset from Ruo Zhi Ba
por: He, Ruiqi, et al.
Publicado: (2024)

On the (In)Effectiveness of Large Language Models for Chinese Text Correction
por: Li, Yinghui, et al.
Publicado: (2023)

Evaluating Chinese Ambiguity Understanding in Large Language Models
por: Mo, Junwen, et al.
Publicado: (2026)

GEB-1.3B: Open Lightweight Large Language Model
por: Wu, Jie, et al.
Publicado: (2024)

INACIA: Integrating Large Language Models in Brazilian Audit Courts: Opportunities and Challenges
por: Pereira, Jayr, et al.
Publicado: (2024)

Impact of Fine-Tuning Methods on Memorization in Large Language Models
por: Hou, Jie, et al.
Publicado: (2025)

INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance
por: Chen, Shisong, et al.
Publicado: (2025)

WenyanGPT: A Large Language Model for Classical Chinese Tasks
por: Yao, Xinyu, et al.
Publicado: (2025)

LAiW: A Chinese Legal Large Language Models Benchmark
por: Dai, Yongfu, et al.
Publicado: (2023)

CHBench: A Chinese Dataset for Evaluating Health in Large Language Models
por: Guo, Chenlu, et al.
Publicado: (2024)

Systematic Framework of Application Methods for Large Language Models in Language Sciences
por: Sun, Kun, et al.
Publicado: (2025)

InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning
por: Zhu, Guanghao, et al.
Publicado: (2025)

EventSum: A Large-Scale Event-Centric Summarization Dataset for Chinese Multi-News Documents
por: Zhu, Mengna, et al.
Publicado: (2024)

CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation
por: Yu, Guangya, et al.
Publicado: (2025)

Small Language Models as Effective Guides for Large Language Models in Chinese Relation Extraction
por: Tang, Xuemei, et al.
Publicado: (2024)

CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model
por: Lei, Yang, et al.
Publicado: (2023)

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	"es"
VUFIND_SESSION	"2d78db941e90c22ca322bd60c2a2e979"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790854435.0759 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "2d78db941e90c22ca322bd60c2a2e979" ]`]
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=es; VUFIND_SESSION=2d78db941e90c22ca322bd60c2a2e979"
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	"1476"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2510_09297/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2510_09297/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790854435.0648
REQUEST_TIME	1790854435

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler