The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Braun, Christian, Lilienbeck, Alexander, Mentjukov, Daniel
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Improving Legal Judgement Prediction in Romanian with Long Text Encoders
di: Masala, Mihai, et al.
Pubblicazione: (2024)

From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation
di: Graus, David
Pubblicazione: (2026)

On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education
di: Wendlinger, Lorenz, et al.
Pubblicazione: (2024)

Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts
di: Hossain, Moinul, et al.
Pubblicazione: (2026)

IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning
di: Joshi, Abhinav, et al.
Pubblicazione: (2024)

LLMs in Interpreting Legal Documents
di: Corbo, Simone
Pubblicazione: (2025)

LegalCore: A Dataset for Event Coreference Resolution in Legal Documents
di: Wei, Kangda, et al.
Pubblicazione: (2025)

Making Implicit Premises Explicit in Logical Understanding of Enthymemes
di: Feng, Xuyao, et al.
Pubblicazione: (2026)

Improving Long Text Understanding with Knowledge Distilled from Summarization Model
di: Liu, Yan, et al.
Pubblicazione: (2024)

PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
di: Ni, Feng, et al.
Pubblicazione: (2025)

LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning
di: Mao, Yansheng, et al.
Pubblicazione: (2024)

Structured Definitions and Segmentations for Legal Reasoning in LLMs: A Study on Indian Legal Data
di: Khatri, Mann, et al.
Pubblicazione: (2025)

<SOG_k>: One LLM Token for Explicit Graph Structural Understanding
di: Wu, Jingyao, et al.
Pubblicazione: (2026)

LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification
di: Nigam, Shubham Kumar, et al.
Pubblicazione: (2025)

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
di: Gero, Zelalem, et al.
Pubblicazione: (2024)

LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text
di: Bernsohn, Dor, et al.
Pubblicazione: (2024)

ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts
di: Duong, Nhung Thi-Hong, et al.
Pubblicazione: (2026)

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
di: Mehta, Nikhil, et al.
Pubblicazione: (2023)

Structured Document Translation via Format Reinforcement Learning
di: Song, Haiyue, et al.
Pubblicazione: (2025)

MARRO: Multi-headed Attention for Rhetorical Role Labeling in Legal Documents
di: Bambroo, Purbid, et al.
Pubblicazione: (2025)

DeepResearch-Slice: Bridging the Retrieval-Utilization Gap via Explicit Text Slicing
di: Lu, Shuo, et al.
Pubblicazione: (2025)

Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
di: Li, Yunzhe, et al.
Pubblicazione: (2023)

RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns
di: Chen, Xin, et al.
Pubblicazione: (2025)

Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts
di: Give, Louis, et al.
Pubblicazione: (2024)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
di: Braun, Joschka
Pubblicazione: (2026)

Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games
di: Zhao, Juntu, et al.
Pubblicazione: (2025)

HLDC: Hindi Legal Documents Corpus
di: Kapoor, Arnav, et al.
Pubblicazione: (2022)

Can Small Models Reason About Legal Documents? A Comparative Study
di: Vaddi, Snehit
Pubblicazione: (2026)

Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model
di: Lin, Chun-Hsien, et al.
Pubblicazione: (2024)

MILPaC: A Novel Benchmark for Evaluating Translation of Legal Text to Indian Languages
di: Mahapatra, Sayan, et al.
Pubblicazione: (2023)

Structured Attention Matters to Multimodal LLMs in Document Understanding
di: Liu, Chang, et al.
Pubblicazione: (2025)

Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
di: Dahl, Matthew, et al.
Pubblicazione: (2024)

Exploring Large Language Models and Hierarchical Frameworks for Classification of Large Unstructured Legal Documents
di: Prasad, Nishchal, et al.
Pubblicazione: (2024)

Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models
di: Nguyen, Hai-Long, et al.
Pubblicazione: (2024)

Guidelines for the Annotation and Visualization of Legal Argumentation Structures in Chinese Judicial Decisions
di: Chen, Kun, et al.
Pubblicazione: (2026)

Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models
di: Kim, Yeeun, et al.
Pubblicazione: (2024)

Aligning Language Models for Icelandic Legal Text Summarization
di: Harðarson, Þórir Hrafn, et al.
Pubblicazione: (2025)

AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures
di: Zhang, Situo, et al.
Pubblicazione: (2024)

Natural Language Processing in the Legal Domain
di: Hartung, Dirk, et al.
Pubblicazione: (2023)

Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study
di: Ovcharov, Volodymyr
Pubblicazione: (2026)

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	"3e88c2cd9bfc8f370a5e18071c5b4cfc"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790983032.4302 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "3e88c2cd9bfc8f370a5e18071c5b4cfc" ]`]
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=3e88c2cd9bfc8f370a5e18071c5b4cfc"
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	"35767"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_12837/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2505_12837/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790983032.4145
REQUEST_TIME	1790983032

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler