@inproceedings{bao-etal-2025-permitted,
title = "Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models",
author = "Bao, Wenrui and
Wang, Kai and
Luo, Siqiang and
Li, Xiang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.722/",
pages = "13390--13405",
ISBN = "979-8-89176-335-7",
abstract = "With the advancement of large language models (LLMs), recent research has raised concerns about their controllability.. In this paper, we argue for the importance of Knowledge-Constrained Responsiveness (KCR), ensuring that LLMs comply with human-defined constraints. However, KCR is an implicit and unobservable capability of LLMs, functioning as a black box that currently eludes quantitative assessment. To address this issue, we first introduce the definition of ``permitted boundary'' and define the ``boundary bias'' to depict KCR. We propose six metrics to quantify the boundary bias of LLMs and subsequently assess the KCR. Furthermore, we establish a benchmark with two new datasets, KCR-SimpleQA and KCR-WebNLG, to evaluate the performance of LLMs. Our extensive experiments show that several tested LLMs still struggle to varying degrees when adhering to constraints, especially without the corresponding knowledge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2025-permitted">
<titleInfo>
<title>Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenrui</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqiang</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</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>With the advancement of large language models (LLMs), recent research has raised concerns about their controllability.. In this paper, we argue for the importance of Knowledge-Constrained Responsiveness (KCR), ensuring that LLMs comply with human-defined constraints. However, KCR is an implicit and unobservable capability of LLMs, functioning as a black box that currently eludes quantitative assessment. To address this issue, we first introduce the definition of “permitted boundary” and define the “boundary bias” to depict KCR. We propose six metrics to quantify the boundary bias of LLMs and subsequently assess the KCR. Furthermore, we establish a benchmark with two new datasets, KCR-SimpleQA and KCR-WebNLG, to evaluate the performance of LLMs. Our extensive experiments show that several tested LLMs still struggle to varying degrees when adhering to constraints, especially without the corresponding knowledge.</abstract>
<identifier type="citekey">bao-etal-2025-permitted</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.722/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>13390</start>
<end>13405</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models
%A Bao, Wenrui
%A Wang, Kai
%A Luo, Siqiang
%A Li, Xiang
%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 bao-etal-2025-permitted
%X With the advancement of large language models (LLMs), recent research has raised concerns about their controllability.. In this paper, we argue for the importance of Knowledge-Constrained Responsiveness (KCR), ensuring that LLMs comply with human-defined constraints. However, KCR is an implicit and unobservable capability of LLMs, functioning as a black box that currently eludes quantitative assessment. To address this issue, we first introduce the definition of “permitted boundary” and define the “boundary bias” to depict KCR. We propose six metrics to quantify the boundary bias of LLMs and subsequently assess the KCR. Furthermore, we establish a benchmark with two new datasets, KCR-SimpleQA and KCR-WebNLG, to evaluate the performance of LLMs. Our extensive experiments show that several tested LLMs still struggle to varying degrees when adhering to constraints, especially without the corresponding knowledge.
%U https://aclanthology.org/2025.findings-emnlp.722/
%P 13390-13405
Markdown (Informal)
[Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models](https://aclanthology.org/2025.findings-emnlp.722/) (Bao et al., Findings 2025)
ACL