Self-Critique and Refinement for Faithful Natural Language Explanations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yingming, Atanasova, Pepa
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

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework
por: Sun, Jingyi, et al.
Publicado: (2024)

Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models
por: Sun, Jingyi, et al.
Publicado: (2025)

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
por: Sun, Jingyi, et al.
Publicado: (2026)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
por: Wang, Qianli, et al.
Publicado: (2026)

Learning from Self Critique and Refinement for Faithful LLM Summarization
por: Hu, Ting-Yao, et al.
Publicado: (2025)

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
por: Yu, Haeun, et al.
Publicado: (2024)

Graph-Guided Textual Explanation Generation Framework
por: Yuan, Shuzhou, et al.
Publicado: (2024)

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
por: Islam, Sekh Mainul, et al.
Publicado: (2025)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
por: Li, Yansi, et al.
Publicado: (2025)

On Measuring Faithfulness or Self-consistency of Natural Language Explanations
por: Parcalabescu, Letitia, et al.
Publicado: (2023)

From Critique to Clarity: A Pathway to Faithful and Personalized Code Explanations with Large Language Models
por: Xu, Zexing, et al.
Publicado: (2024)

Investigating Training and Generalization in Faithful Self-Explanations of Large Language Models
por: Doi, Tomoki, et al.
Publicado: (2025)

Training Language Model to Critique for Better Refinement
por: Yu, Tianshu, et al.
Publicado: (2025)

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment
por: Bhan, Milan, et al.
Publicado: (2025)

CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation
por: Bandyopadhyay, Dibyanayan, et al.
Publicado: (2025)

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
por: Wojciechowski, Adam, et al.
Publicado: (2024)

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
por: Yeo, Wei Jie, et al.
Publicado: (2024)

Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
por: Fragkathoulas, Christos, et al.
Publicado: (2024)

FaithLM: Towards Faithful Explanations for Large Language Models
por: Chuang, Yu-Neng, et al.
Publicado: (2024)

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
por: Wang, Qianli, et al.
Publicado: (2024)

Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving
por: Quan, Xin, et al.
Publicado: (2024)

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
por: Marjanović, Sara Vera, et al.
Publicado: (2024)

Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning
por: Ho, Duc Hieu, et al.
Publicado: (2025)

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
por: Liu, Gabrielle Kaili-May, et al.
Publicado: (2025)

Grounding Natural Language to SQL Translation with Data-Based Self-Explanations
por: Fan, Yuankai, et al.
Publicado: (2024)

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
por: Mahale, Ajay Pravin
Publicado: (2026)

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
por: Agarwal, Chirag, et al.
Publicado: (2024)

Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models
por: Sovrano, Francesco, et al.
Publicado: (2026)

Situated Natural Language Explanations
por: Zhu, Zining, et al.
Publicado: (2023)

Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models
por: Gong, Xilin, et al.
Publicado: (2026)

Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
por: Li, Dongfang, et al.
Publicado: (2023)

Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning
por: Zhu, Chenghao, et al.
Publicado: (2025)

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
por: Siegel, Noah Y., et al.
Publicado: (2025)

The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
por: Siegel, Noah Y., et al.
Publicado: (2024)

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
por: Zhou, Changzhi, et al.
Publicado: (2025)

Towards Faithful Model Explanation in NLP: A Survey
por: Lyu, Qing, et al.
Publicado: (2022)

Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations
por: Matton, Katie, et al.
Publicado: (2025)

Digital Socrates: Evaluating LLMs through Explanation Critiques
por: Gu, Yuling, et al.
Publicado: (2023)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
por: Zhao, Weixiang, et al.
Publicado: (2026)

Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations
por: Manna, Supriya, et al.
Publicado: (2024)

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	"es"
VUFIND_SESSION	"c046ea49ecb9f06d05e24a94f8b49925"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790987116.709 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c046ea49ecb9f06d05e24a94f8b49925" ]`]
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=es; VUFIND_SESSION=c046ea49ecb9f06d05e24a94f8b49925; 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	"216.73.217.142"
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	"1560"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_22823/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_22823/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790987116.6929
REQUEST_TIME	1790987116

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler