TriBench-Ko: Evaluating LLM Risks in Judicial Workflows

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Haesung, Choi, Gyubin, Lee, Eun-Ju, Lee, So-Min, Ko, Youkang, Lim, Dogyoon, Jang, Sung-Kyoung, Jo, Yohan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators
di: Lim, Sungjib, et al.
Pubblicazione: (2025)

Context-Robust Knowledge Editing for Language Models
di: Park, Haewon, et al.
Pubblicazione: (2025)

Human Psychometric Questionnaires Mischaracterize LLM Behavior
di: Song, Woojung, et al.
Pubblicazione: (2025)

Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
di: Lee, Jonggeun, et al.
Pubblicazione: (2025)

Resolvent approaches to elliptic regularity in stationary Fokker-Planck equations
di: Lee, Haesung
Pubblicazione: (2026)

Uniform approximation by harmonic polynomials for solving the Dirichlet problem of Laplace's equation on a disk
di: Lee, Haesung
Pubblicazione: (2024)

Analysis of linear elliptic equations with general drifts and $L^1$-zero-order terms
di: Lee, Haesung
Pubblicazione: (2024)

Well-posedness of linear elliptic equations with $L^d$-drifts under divergence-type conditions
di: Lee, Haesung
Pubblicazione: (2026)

Local elliptic regularity for solutions to stationary Fokker-Planck equations via Dirichlet forms and resolvents
di: Lee, Haesung
Pubblicazione: (2024)

Quantitative analysis for $L^2$-estimates in linear elliptic equations via divergence-free transformation
di: Lee, Haesung
Pubblicazione: (2025)

Remarks on well-posedness for linear elliptic equations via divergence-free transformation
di: Lee, Haesung
Pubblicazione: (2026)

Cholesky decomposition and well-posedness of Cauchy problem for Fokker-Planck equations with unbounded coefficients
di: Lee, Haesung
Pubblicazione: (2025)

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples
di: Pyun, Haesung, et al.
Pubblicazione: (2025)

Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions
di: Park, Yoonah, et al.
Pubblicazione: (2025)

KL for a KL: On-Policy Distillation with Control Variate Baseline
di: Oh, Minjae, et al.
Pubblicazione: (2026)

Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items
di: Han, Jongwook, et al.
Pubblicazione: (2025)

KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark
di: Jang, Seongbo, et al.
Pubblicazione: (2024)

PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness Ratings
di: Kim, Junseo, et al.
Pubblicazione: (2025)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
di: Lee, Yohan, et al.
Pubblicazione: (2026)

CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation
di: Lee, Gyubin, et al.
Pubblicazione: (2026)

Polyp Segmentation Using Wavelet-Based Cross-Band Integration for Enhanced Boundary Representation
di: Oh, Haesung, et al.
Pubblicazione: (2026)

Pointwise well-posedness results for degenerate Itô-SDEs with locally bounded drifts
di: Lee, Haesung, et al.
Pubblicazione: (2024)

Uniqueness in law for singular degenerate SDEs with respect to a (sub-)invariant measure
di: Lee, Haesung, et al.
Pubblicazione: (2024)

Robust error estimates of PINN in one-dimensional boundary value problems for linear elliptic equations
di: Yoo, Jihahm, et al.
Pubblicazione: (2024)

Weighted Helmholtz--Hodge decompositions, Lyapunov functions, and invariant measures
di: Lee, Haesung, et al.
Pubblicazione: (2026)

ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput
di: Kim, Junsoo, et al.
Pubblicazione: (2025)

The impact of frailty syndrome on skeletal muscle histology: preventive effects of exercise
di: Fujue Ji, et al.
Pubblicazione: (2025)

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
di: Jang, Sangwon, et al.
Pubblicazione: (2024)

Carbon Source–Dependent Metabolic Shift of Lactobacillus gasseri Reveals Condition‐Specific Bioactive Metabolites for Postbiotic Applications
di: Dong Young Lee, et al.
Pubblicazione: (2026)

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
di: Jang, Sangwon, et al.
Pubblicazione: (2025)

SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era
di: Jang, Han, et al.
Pubblicazione: (2026)

KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
di: Ko, Donghyeon, et al.
Pubblicazione: (2025)

KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
di: Kim, Jinyoung, et al.
Pubblicazione: (2026)

MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models
di: Jang, Han, et al.
Pubblicazione: (2026)

CONMOD: Controllable Neural Frame-based Modulation Effects
di: Lee, Gyubin, et al.
Pubblicazione: (2024)

Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding
di: Jung, Sungmok, et al.
Pubblicazione: (2026)

SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
di: Lee, Jungho, et al.
Pubblicazione: (2024)

Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation
di: Lee, Seunghoon, et al.
Pubblicazione: (2023)

Spatially explicit population modeling with habitat preferential movement of Glis glis (Edible dormouse)
di: Choi, Jeehye, et al.
Pubblicazione: (2025)

Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark
di: Park, Chanjun, et al.
Pubblicazione: (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	"it"
ui	"standard"
VUFIND_SESSION	"5e8a09298d03c1ce5b24404de5514253"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1791214106.5031 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "5e8a09298d03c1ce5b24404de5514253" ]`]
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=it; ui=standard; VUFIND_SESSION=5e8a09298d03c1ce5b24404de5514253"
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	"216.73.217.58"
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	"25698"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_03792/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_03792/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1791214106.4989
REQUEST_TIME	1791214106

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler