@inproceedings{park-etal-2025-truebench,
title = "{TRUEB}ench: Can {LLM} Response Meet Real-world Constraints as Productivity Assistant?",
author = "Park, Jiho and
Song, Jongyoon and
Choi, Minjin and
Heo, Kyuho and
Huh, Taehun and
Kim, Ji Won",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.776/",
doi = "10.18653/v1/2025.findings-emnlp.776",
pages = "14383--14409",
ISBN = "979-8-89176-335-7",
abstract = "Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient multilinguality, (ii) fail to capture the implicit constraints inherent in user requests, and (iii) overlook the complexities of multi-turn dialogue. To address these critical gaps and provide a more realistic assessment, we introduce TRUEBench (Trustworthy Real-world Usage Evaluation Benchmark), a novel benchmark specifically designed for LLM-based productivity assistants. TRUEBench distinguishes itself by featuring input prompts across 12 languages, incorporating intra-instance multilingual instructions, employing rigorous evaluation criteria to capture both explicit and implicit constraints, and including complex multi-turn dialogue scenarios with both accumulating constraints and context switches. Furthermore, to ensure reliability in evaluation, we refined constraints using an LLM validator. Extensive experiments demonstrate that TRUEBench presents significantly greater challenges than existing benchmarks; for instance, a strong model like OpenAI o1 achieved only a 69.07{\%} overall pass rate. TRUEBench offers a demanding and realistic assessment of LLMs in practical productivity settings, highlighting their capabilities and limitations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2025-truebench">
<titleInfo>
<title>TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiho</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jongyoon</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyuho</namePart>
<namePart type="family">Heo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taehun</namePart>
<namePart type="family">Huh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="given">Won</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient multilinguality, (ii) fail to capture the implicit constraints inherent in user requests, and (iii) overlook the complexities of multi-turn dialogue. To address these critical gaps and provide a more realistic assessment, we introduce TRUEBench (Trustworthy Real-world Usage Evaluation Benchmark), a novel benchmark specifically designed for LLM-based productivity assistants. TRUEBench distinguishes itself by featuring input prompts across 12 languages, incorporating intra-instance multilingual instructions, employing rigorous evaluation criteria to capture both explicit and implicit constraints, and including complex multi-turn dialogue scenarios with both accumulating constraints and context switches. Furthermore, to ensure reliability in evaluation, we refined constraints using an LLM validator. Extensive experiments demonstrate that TRUEBench presents significantly greater challenges than existing benchmarks; for instance, a strong model like OpenAI o1 achieved only a 69.07% overall pass rate. TRUEBench offers a demanding and realistic assessment of LLMs in practical productivity settings, highlighting their capabilities and limitations.</abstract>
<identifier type="citekey">park-etal-2025-truebench</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.776</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.776/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>14383</start>
<end>14409</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?
%A Park, Jiho
%A Song, Jongyoon
%A Choi, Minjin
%A Heo, Kyuho
%A Huh, Taehun
%A Kim, Ji Won
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F park-etal-2025-truebench
%X Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-following capabilities. Current benchmarks often (i) lack sufficient multilinguality, (ii) fail to capture the implicit constraints inherent in user requests, and (iii) overlook the complexities of multi-turn dialogue. To address these critical gaps and provide a more realistic assessment, we introduce TRUEBench (Trustworthy Real-world Usage Evaluation Benchmark), a novel benchmark specifically designed for LLM-based productivity assistants. TRUEBench distinguishes itself by featuring input prompts across 12 languages, incorporating intra-instance multilingual instructions, employing rigorous evaluation criteria to capture both explicit and implicit constraints, and including complex multi-turn dialogue scenarios with both accumulating constraints and context switches. Furthermore, to ensure reliability in evaluation, we refined constraints using an LLM validator. Extensive experiments demonstrate that TRUEBench presents significantly greater challenges than existing benchmarks; for instance, a strong model like OpenAI o1 achieved only a 69.07% overall pass rate. TRUEBench offers a demanding and realistic assessment of LLMs in practical productivity settings, highlighting their capabilities and limitations.
%R 10.18653/v1/2025.findings-emnlp.776
%U https://aclanthology.org/2025.findings-emnlp.776/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.776
%P 14383-14409
Markdown (Informal)
[TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?](https://aclanthology.org/2025.findings-emnlp.776/) (Park et al., Findings 2025)
ACL