RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Oh, Minhae, Kim, Jeonghye, Lee, Nakyung, Seo, Donggeon, Kim, Taeuk, Lee, Jungwoo
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation
par: Lee, Nakyung, et autres
Publié: (2025)

Efficient Process Reward Modeling via Contrastive Mutual Information
par: Lee, Nakyung, et autres
Publié: (2026)

MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation
par: Lee, Jungyeon, et autres
Publié: (2025)

Database Normalization via Dual-LLM Self-Refinement
par: Jo, Eunjae, et autres
Publié: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
par: Kim, Jeonghye, et autres
Publié: (2026)

SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation
par: Kim, Jungwoo, et autres
Publié: (2025)

STEPER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models
par: Lee, Kyumin, et autres
Publié: (2025)

FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning
par: Kim, Seunghee, et autres
Publié: (2024)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
par: Li, Yuan, et autres
Publié: (2025)

Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
par: Kim, Jisu, et autres
Publié: (2025)

KGMEL: Knowledge Graph-Enhanced Multimodal Entity Linking
par: Kim, Juyeon, et autres
Publié: (2025)

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
par: Mishra, Venkatesh, et autres
Publié: (2025)

AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline
par: Kim, Dongkyu, et autres
Publié: (2024)

ADVICE: Answer-Dependent Verbalized Confidence Estimation
par: Seo, Ki Jung, et autres
Publié: (2025)

Revisiting the Impact of Pursuing Modularity for Code Generation
par: Kang, Deokyeong, et autres
Publié: (2024)

StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning
par: Yu, Yuanqing, et autres
Publié: (2024)

When to Speak, When to Abstain: Contrastive Decoding with Abstention
par: Kim, Hyuhng Joon, et autres
Publié: (2024)

Assessing LLM Reasoning Steps via Principal Knowledge Grounding
par: Hwang, Hyeon, et autres
Publié: (2025)

Evaluating Step-by-step Reasoning Traces: A Survey
par: Lee, Jinu, et autres
Publié: (2025)

Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
par: Kim, Jun Seo, et autres
Publié: (2025)

What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
par: Do, Heejin, et autres
Publié: (2025)

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
par: Kim, Jeonghye, et autres
Publié: (2026)

BlendX: Complex Multi-Intent Detection with Blended Patterns
par: Yoon, Yejin, et autres
Publié: (2024)

In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
par: Kim, Jaehoon, et autres
Publié: (2025)

Infinite Mask Diffusion for Few-Step Distillation
par: Yoo, Jaehoon, et autres
Publié: (2026)

Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
par: Kim, Youna, et autres
Publié: (2024)

Systematic Review on Healthcare Systems Engineering utilizing ChatGPT
par: Kim, Jungwoo, et autres
Publié: (2024)

ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision
par: Lee, Dosung, et autres
Publié: (2025)

Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts
par: Long, Quanyu, et autres
Publié: (2025)

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
par: Tyagi, Nemika, et autres
Publié: (2024)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
par: Kim, Jeonghye, et autres
Publié: (2025)

Multi-Step Semantic Reasoning in Generative Retrieval
par: Dong, Steven, et autres
Publié: (2026)

A Two-Step Approach for Data-Efficient French Pronunciation Learning
par: Lee, Hoyeon, et autres
Publié: (2024)

ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking
par: Kim, Boyoung, et autres
Publié: (2025)

Does Localization Inform Unlearning? A Rigorous Examination of Local Parameter Attribution for Knowledge Unlearning in Language Models
par: Lee, Hwiyeong, et autres
Publié: (2025)

Latent Preference Modeling for Cross-Session Personalized Tool Calling
par: Yoon, Yejin, et autres
Publié: (2026)

ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
par: Oh, Jungwoo, et autres
Publié: (2026)

Instruct Large Language Models to Generate Scientific Literature Survey Step by Step
par: Lai, Yuxuan, et autres
Publié: (2024)

Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning
par: Huang, Xinyi
Publié: (2026)

Evaluating Step-by-Step Reasoning through Symbolic Verification
par: Zhang, Yi-Fan, et autres
Publié: (2022)

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	"fr"
VUFIND_SESSION	"f10c210fd8ec5bb23b168695dd64cef6"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790894881.7071 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "f10c210fd8ec5bb23b168695dd64cef6" ]`]
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=fr; VUFIND_SESSION=f10c210fd8ec5bb23b168695dd64cef6; 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	"12002"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2506_08625/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2506_08625/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790894881.7031
REQUEST_TIME	1790894881

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler