@inproceedings{zhang-2026-pcp,
title = "{PCP}: A Controlled Benchmark for Pragmatic Intention Recognition in Clinical Communication",
author = "Zhang, Kun",
editor = "Sousa-Silva, Rui and
Lopes Cardoso, Henrique and
Koponen, Maarit and
Pareja-Lora, Antonio",
booktitle = "Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era ({LUHME} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.luhme-1.1/",
pages = "1--24",
ISBN = "979-8-89176-471-2",
abstract = "Medical LLMs are commonly evaluated on factual question answering, summarization, and explicitly stated clinical information, but less on pragmatic understanding: recovering intended meaning from indirectness, hedging, urgency cues, politeness, and implicature. We present PCP, a 3,533-item benchmark for pragmatic intention recognition in clinical communication, with a controlled synthetic Core split, a close-distractor Hard split, and a small externally grounded Real-Clean split derived from public doctor{--}patient dialogue datasets. PCP combines answer-choice artifact audits with blind human validation of all Hard and Real-Clean items plus a 300-item Core sample, and targeted expert review of 280 items. Across eleven systems (six API-accessed, five open-weight), our main finding is a recognition-vs-naming dissociation: ten of the eleven select the intended clinical action at 95.5{--}98.4{\%} aggregate accuracy but name the pragmatic phenomenon licensing it at only 56.6{--}64.5{\%}, a 32{--}40 pp gap on the same items. Recognition is also split-dependent: API-accessed models are near ceiling on PCP-Core (98.7{--}99.8{\%}) but drop on PCP-Hard-469 (83.4{--}90.6{\%}) and PCP-Real-Clean-64 (79.7{--}90.6{\%}), so broad controlled probes can mask difficulty exposed by close distractors and externally grounded cases. Because gold actions are often the most medically defensible choice, accuracy is a confound-limited estimate; PCP is an evaluation resource for controlled clinical-pragmatic inference, not for deployment readiness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2026-pcp">
<titleInfo>
<title>PCP: A Controlled Benchmark for Pragmatic Intention Recognition in Clinical Communication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhang</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 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Sousa-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja-Lora</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">979-8-89176-471-2</identifier>
</relatedItem>
<abstract>Medical LLMs are commonly evaluated on factual question answering, summarization, and explicitly stated clinical information, but less on pragmatic understanding: recovering intended meaning from indirectness, hedging, urgency cues, politeness, and implicature. We present PCP, a 3,533-item benchmark for pragmatic intention recognition in clinical communication, with a controlled synthetic Core split, a close-distractor Hard split, and a small externally grounded Real-Clean split derived from public doctor–patient dialogue datasets. PCP combines answer-choice artifact audits with blind human validation of all Hard and Real-Clean items plus a 300-item Core sample, and targeted expert review of 280 items. Across eleven systems (six API-accessed, five open-weight), our main finding is a recognition-vs-naming dissociation: ten of the eleven select the intended clinical action at 95.5–98.4% aggregate accuracy but name the pragmatic phenomenon licensing it at only 56.6–64.5%, a 32–40 pp gap on the same items. Recognition is also split-dependent: API-accessed models are near ceiling on PCP-Core (98.7–99.8%) but drop on PCP-Hard-469 (83.4–90.6%) and PCP-Real-Clean-64 (79.7–90.6%), so broad controlled probes can mask difficulty exposed by close distractors and externally grounded cases. Because gold actions are often the most medically defensible choice, accuracy is a confound-limited estimate; PCP is an evaluation resource for controlled clinical-pragmatic inference, not for deployment readiness.</abstract>
<identifier type="citekey">zhang-2026-pcp</identifier>
<location>
<url>https://aclanthology.org/2026.luhme-1.1/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PCP: A Controlled Benchmark for Pragmatic Intention Recognition in Clinical Communication
%A Zhang, Kun
%Y Sousa-Silva, Rui
%Y Lopes Cardoso, Henrique
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-471-2
%F zhang-2026-pcp
%X Medical LLMs are commonly evaluated on factual question answering, summarization, and explicitly stated clinical information, but less on pragmatic understanding: recovering intended meaning from indirectness, hedging, urgency cues, politeness, and implicature. We present PCP, a 3,533-item benchmark for pragmatic intention recognition in clinical communication, with a controlled synthetic Core split, a close-distractor Hard split, and a small externally grounded Real-Clean split derived from public doctor–patient dialogue datasets. PCP combines answer-choice artifact audits with blind human validation of all Hard and Real-Clean items plus a 300-item Core sample, and targeted expert review of 280 items. Across eleven systems (six API-accessed, five open-weight), our main finding is a recognition-vs-naming dissociation: ten of the eleven select the intended clinical action at 95.5–98.4% aggregate accuracy but name the pragmatic phenomenon licensing it at only 56.6–64.5%, a 32–40 pp gap on the same items. Recognition is also split-dependent: API-accessed models are near ceiling on PCP-Core (98.7–99.8%) but drop on PCP-Hard-469 (83.4–90.6%) and PCP-Real-Clean-64 (79.7–90.6%), so broad controlled probes can mask difficulty exposed by close distractors and externally grounded cases. Because gold actions are often the most medically defensible choice, accuracy is a confound-limited estimate; PCP is an evaluation resource for controlled clinical-pragmatic inference, not for deployment readiness.
%U https://aclanthology.org/2026.luhme-1.1/
%P 1-24
Markdown (Informal)
[PCP: A Controlled Benchmark for Pragmatic Intention Recognition in Clinical Communication](https://aclanthology.org/2026.luhme-1.1/) (Zhang, LUHME 2026)
ACL