The Extractive-Abstractive Spectrum: Uncovering Verifiability Trade-offs in LLM Generations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Worledge, Theodora, Hashimoto, Tatsunori, Guestrin, Carlos
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Benchmarking Distributional Alignment of Large Language Models
por: Meister, Nicole, et al.
Publicado: (2024)

Synthesizing Scientific Summaries: An Extractive and Abstractive Approach
por: Sharma, Grishma, et al.
Publicado: (2024)

Hybrid Extractive Abstractive Summarization for Multilingual Sentiment Analysis
por: Krasitskii, Mikhail, et al.
Publicado: (2025)

Sentiment-Aware Extractive and Abstractive Summarization for Unstructured Text Mining
por: Liu, Junyi, et al.
Publicado: (2025)

From News to Summaries: Building a Hungarian Corpus for Extractive and Abstractive Summarization
por: Barta, Botond, et al.
Publicado: (2024)

Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework
por: Wu, Yuping, et al.
Publicado: (2024)

The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
por: Si, Chenglei, et al.
Publicado: (2025)

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
por: Yu, Qinan, et al.
Publicado: (2026)

Language Models with Conformal Factuality Guarantees
por: Mohri, Christopher, et al.
Publicado: (2024)

Understanding LLM Reasoning for Abstractive Summarization
por: Yuan, Haohan, et al.
Publicado: (2025)

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
por: Si, Chenglei, et al.
Publicado: (2024)

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback
por: Dubois, Yann, et al.
Publicado: (2023)

Understanding Finetuning for Factual Knowledge Extraction
por: Ghosal, Gaurav, et al.
Publicado: (2024)

Improving Pretraining Data Using Perplexity Correlations
por: Thrush, Tristan, et al.
Publicado: (2024)

Linguistic Calibration of Long-Form Generations
por: Band, Neil, et al.
Publicado: (2024)

Scalable and Domain-General Abstractive Proposition Segmentation
por: Hosseini, Mohammad Javad, et al.
Publicado: (2024)

Discovering Implicit Large Language Model Alignment Objectives
por: Chen, Edward, et al.
Publicado: (2026)

Generating Zero-shot Abstractive Explanations for Rumour Verification
por: Bilal, Iman Munire, et al.
Publicado: (2024)

Personalized Abstractive Summarization by Tri-agent Generation Pipeline
por: Xiao, Wen, et al.
Publicado: (2023)

Observational Scaling Laws and the Predictability of Language Model Performance
por: Ruan, Yangjun, et al.
Publicado: (2024)

metaTextGrad: Automatically optimizing language model optimizers
por: Xu, Guowei, et al.
Publicado: (2025)

Source Identification in Abstractive Summarization
por: Suhara, Yoshi, et al.
Publicado: (2024)

Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening
por: Gan, Chengguang, et al.
Publicado: (2024)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
por: Sun, Yu, et al.
Publicado: (2024)

Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses
por: Ho, Xanh, et al.
Publicado: (2025)

An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs
por: Zhu, Qian, et al.
Publicado: (2026)

Exploring Language Model Generalization in Low-Resource Extractive QA
por: Sengupta, Saptarshi, et al.
Publicado: (2024)

Robust Distortion-free Watermarks for Language Models
por: Kuditipudi, Rohith, et al.
Publicado: (2023)

LLatrieval: LLM-Verified Retrieval for Verifiable Generation
por: Li, Xiaonan, et al.
Publicado: (2023)

Fair Abstractive Summarization of Diverse Perspectives
por: Zhang, Yusen, et al.
Publicado: (2023)

Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches
por: Junias, Obed, et al.
Publicado: (2025)

Putting It All into Context: Simplifying Agents with LCLMs
por: Jiang, Mingjian, et al.
Publicado: (2025)

Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
por: Handa, Gunmay, et al.
Publicado: (2025)

How Private are Language Models in Abstractive Summarization?
por: Hughes, Anthony, et al.
Publicado: (2024)

Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
por: Dubois, Yann, et al.
Publicado: (2024)

On the Learnability of Watermarks for Language Models
por: Gu, Chenchen, et al.
Publicado: (2023)

Reasoning to Learn from Latent Thoughts
por: Ruan, Yangjun, et al.
Publicado: (2025)

Integrating Supervised Extractive and Generative Language Models for Suicide Risk Evidence Summarization
por: Tanaka, Rika, et al.
Publicado: (2024)

Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts
por: Feng, Jiahai, et al.
Publicado: (2024)

Semantic Search as Extractive Paraphrase Span Detection
por: Kanerva, Jenna, et al.
Publicado: (2021)

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" => 1790854444.8588 "_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	"49269"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2411_17375/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_17375/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790854444.8422
REQUEST_TIME	1790854444

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler