@inproceedings{kundu-etal-2026-trust,
title = "{TRUST}-{BENCH}: A Synthetic {J}apanese Financial-Group Benchmark for Enterprise Document Access in Coding Agents",
author = "Kundu, Shamik and
Mekala, Anand and
Yamasaki, Kazutaka",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.6/",
pages = "53--64",
ISBN = "979-8-89176-466-8",
abstract = "In large financial institutions, what code should do is rarely recoverable from code alone: the authoritative rules live in internal business documents that are largely unreachable to coding agents. Benchmarks built on public repositories therefore cannot measure what reaching those documents is worth. We present TRUST-BENCH, a fully synthetic benchmark that measures the effect of enterprise document availability and of the channel through which it is delivered: the codebase of a fictional Japanese financial group-1,105 programs and 287k lines of code across five languages, a legacy COBOL/PL/I/RPG core of record surrounded by the Java and C periphery paired with 149 Japanese business documents and 93 maintenance tasks. Tasks are graded two ways: an LLM judge scores answers for correctness and completeness, and generated code is compiled, run, and checked against curated test cases.\par We describe the dataset-generation procedure in detail and report results over four context conditions: code only (the baseline); code with the raw documents on disk; code with documents behind a hybrid retrieval tool; and code with documents behind a knowledge-graph tool. Graph-mediated document access raised retrieval-task correctness from 0.68 to 0.94 while the strict build-task pass rate rose from 27{\%} to 91{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kundu-etal-2026-trust">
<titleInfo>
<title>TRUST-BENCH: A Synthetic Japanese Financial-Group Benchmark for Enterprise Document Access in Coding Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shamik</namePart>
<namePart type="family">Kundu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Mekala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazutaka</namePart>
<namePart type="family">Yamasaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>In large financial institutions, what code should do is rarely recoverable from code alone: the authoritative rules live in internal business documents that are largely unreachable to coding agents. Benchmarks built on public repositories therefore cannot measure what reaching those documents is worth. We present TRUST-BENCH, a fully synthetic benchmark that measures the effect of enterprise document availability and of the channel through which it is delivered: the codebase of a fictional Japanese financial group-1,105 programs and 287k lines of code across five languages, a legacy COBOL/PL/I/RPG core of record surrounded by the Java and C periphery paired with 149 Japanese business documents and 93 maintenance tasks. Tasks are graded two ways: an LLM judge scores answers for correctness and completeness, and generated code is compiled, run, and checked against curated test cases.\par We describe the dataset-generation procedure in detail and report results over four context conditions: code only (the baseline); code with the raw documents on disk; code with documents behind a hybrid retrieval tool; and code with documents behind a knowledge-graph tool. Graph-mediated document access raised retrieval-task correctness from 0.68 to 0.94 while the strict build-task pass rate rose from 27% to 91%.</abstract>
<identifier type="citekey">kundu-etal-2026-trust</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.6/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>53</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRUST-BENCH: A Synthetic Japanese Financial-Group Benchmark for Enterprise Document Access in Coding Agents
%A Kundu, Shamik
%A Mekala, Anand
%A Yamasaki, Kazutaka
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F kundu-etal-2026-trust
%X In large financial institutions, what code should do is rarely recoverable from code alone: the authoritative rules live in internal business documents that are largely unreachable to coding agents. Benchmarks built on public repositories therefore cannot measure what reaching those documents is worth. We present TRUST-BENCH, a fully synthetic benchmark that measures the effect of enterprise document availability and of the channel through which it is delivered: the codebase of a fictional Japanese financial group-1,105 programs and 287k lines of code across five languages, a legacy COBOL/PL/I/RPG core of record surrounded by the Java and C periphery paired with 149 Japanese business documents and 93 maintenance tasks. Tasks are graded two ways: an LLM judge scores answers for correctness and completeness, and generated code is compiled, run, and checked against curated test cases.\par We describe the dataset-generation procedure in detail and report results over four context conditions: code only (the baseline); code with the raw documents on disk; code with documents behind a hybrid retrieval tool; and code with documents behind a knowledge-graph tool. Graph-mediated document access raised retrieval-task correctness from 0.68 to 0.94 while the strict build-task pass rate rose from 27% to 91%.
%U https://aclanthology.org/2026.finnlp-1.6/
%P 53-64
Markdown (Informal)
[TRUST-BENCH: A Synthetic Japanese Financial-Group Benchmark for Enterprise Document Access in Coding Agents](https://aclanthology.org/2026.finnlp-1.6/) (Kundu et al., FinNLP 2026)
ACL