Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension:Testing and Evaluation of the NBCE Method

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Guoqing, Fukuyama, Keita, Kishimoto, Kazumasa, Kuroda, Tomohiro
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context
von: Ji, Shihao, et al.
Veröffentlicht: (2026)

Automatic Summarization of Long Documents
von: Chhibbar, Naman, et al.
Veröffentlicht: (2024)

Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding
von: Fei, Weizhi, et al.
Veröffentlicht: (2024)

PolicyLong: Towards On-Policy Context Extension
von: Jia, Junlong, et al.
Veröffentlicht: (2026)

Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs
von: Zhang, Haozhen, et al.
Veröffentlicht: (2024)

A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods
von: Zhang, Yang, et al.
Veröffentlicht: (2024)

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing
von: Broadwater, Keita
Veröffentlicht: (2026)

Benchmarking the Utility of Privacy-Preserving Cox Regression Under Data-Driven Clipping Bounds: A Multi-Dataset Simulation Study
von: Fukuyama, Keita, et al.
Veröffentlicht: (2026)

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels
von: Wei, Lingxiao, et al.
Veröffentlicht: (2024)

ACER: Automatic Language Model Context Extension via Retrieval
von: Gao, Luyu, et al.
Veröffentlicht: (2024)

Robust Counterfactual Explanations under Model Multiplicity Using Multi-Objective Optimization
von: Kinjo, Keita
Veröffentlicht: (2025)

Hallucination Detection-Guided Preference Optimization for Clinical Summarization
von: Seethakantha, Shamanth Kuthpadi, et al.
Veröffentlicht: (2026)

Aligning Evaluation with Clinical Priorities: Calibration, Label Shift, and Error Costs
von: Flores, Gerardo A., et al.
Veröffentlicht: (2025)

An Evolutionary Framework for Automatic Optimization Benchmark Generation via Large Language Models
von: Ono, Yuhiro, et al.
Veröffentlicht: (2026)

Stress Testing Factual Consistency Metrics for Long-Document Summarization
von: Mujahid, Zain Muhammad, et al.
Veröffentlicht: (2025)

CNsum:Automatic Summarization for Chinese News Text
von: Zhao, Yu, et al.
Veröffentlicht: (2025)

A Survey on Transformer Context Extension: Approaches and Evaluation
von: Liu, Yijun, et al.
Veröffentlicht: (2025)

Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference
von: Ma, Guoqing, et al.
Veröffentlicht: (2025)

A Comparative Study of Quality Evaluation Methods for Text Summarization
von: Nguyen, Huyen, et al.
Veröffentlicht: (2024)

Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization
von: Zhong, Yang, et al.
Veröffentlicht: (2025)

Comparing Approaches to Automatic Summarization in Less-Resourced Languages
von: Palen-Michel, Chester, et al.
Veröffentlicht: (2025)

Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications
von: Godbole, Aditi, et al.
Veröffentlicht: (2024)

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs
von: Wornow, Michael, et al.
Veröffentlicht: (2024)

ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs
von: Piya, Fahmida Liza, et al.
Veröffentlicht: (2025)

What's under the hood: Investigating Automatic Metrics on Meeting Summarization
von: Kirstein, Frederic, et al.
Veröffentlicht: (2024)

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs
von: Myers, Skatje, et al.
Veröffentlicht: (2025)

AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context
von: Zhang, Lei, et al.
Veröffentlicht: (2026)

Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling
von: Broadwater, Keita
Veröffentlicht: (2026)

LongSafety: Evaluating Long-Context Safety of Large Language Models
von: Lu, Yida, et al.
Veröffentlicht: (2025)

Analysis of Customer Journeys Using Prototype Detection and Counterfactual Explanations for Sequential Data
von: Kinjo, Keita
Veröffentlicht: (2025)

Leveraging Generative AI for Clinical Evidence Summarization Needs to Ensure Trustworthiness
von: Zhang, Gongbo, et al.
Veröffentlicht: (2023)

Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs
von: Liu, Peidong, et al.
Veröffentlicht: (2025)

Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
von: Lyu, Mengxian, et al.
Veröffentlicht: (2026)

Enhancing Video Summarization with Context Awareness
von: Huynh-Lam, Hai-Dang, et al.
Veröffentlicht: (2024)

TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains
von: Wang, Wanying, et al.
Veröffentlicht: (2024)

DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
von: Choi, Nayoung, et al.
Veröffentlicht: (2026)

Evaluating Long-Context Reasoning in LLM-Based WebAgents
von: Chung, Andy, et al.
Veröffentlicht: (2025)

Question-Answering Based Summarization of Electronic Health Records using Retrieval Augmented Generation
von: Saba, Walid, et al.
Veröffentlicht: (2024)

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
von: Wang, Yidong, et al.
Veröffentlicht: (2023)

Submodular Evaluation Subset Selection in Automatic Prompt Optimization
von: Nian, Jinming, et al.
Veröffentlicht: (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
language	"de"
VUFIND_SESSION	"bac4f3a1d051df90ba1d113eb6f8e37c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790829823.5531 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "bac4f3a1d051df90ba1d113eb6f8e37c" ]`]
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=de; VUFIND_SESSION=bac4f3a1d051df90ba1d113eb6f8e37c; 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	"216.73.216.147"
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	"2829"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2411_08586/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2411_08586/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790829823.5488
REQUEST_TIME	1790829823

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler