@inproceedings{zhang-cong-2026-ba,
title = "To ``Ba'' or Not to ``Ba''? {LLM} Surprisal as a Diagnostic of Context-Sensitive Language Understanding in {L}2 {C}hinese",
author = "Zhang, Shengjie and
Cong, Yan",
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-1.18/",
pages = "227--245",
ISBN = "979-8-89176-471-2",
abstract = "Some difficulties in learning Chinese as a second language (L2 Chinese) involve choosing a sentence pattern that is grammatically well formed but less natural in context. Mandarin ba/SVO choice is one such case: learners may avoid ba when the discourse favors it or extend it to contexts where SVO is more appropriate. Because edit-based correction systems may leave both alternatives unchanged, diagnosing these choices requires sensitivity to discourse context, making the task a targeted test of context-sensitive natural language understanding (NLU). Using 200 controlled discourse contexts, we examine whether autoregressive LLM surprisal can serve as a graded diagnostic of this distinction. Across 21 open-weight models, sentence-level mean surprisal identifies the contextually preferred continuation with a mean model-level accuracy of 87.93{\%}, whereas a MacBERT-based correction baseline leaves most contextually non-preferred continuations unchanged. Relevant context generally lowers surprisal for the intended continuation, and sentence-level scoring is more reliable than first-token scoring, whose interpretation varies with tokenizer granularity. The results suggest that surprisal can complement edit-based correction in L2 pragmatic assessment, while cross-model asymmetries, structural preference biases, and tokenizer effects underscore the need for construction-specific controls and human interpretation when evaluating context-sensitive NLU."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-cong-2026-ba">
<titleInfo>
<title>To “Ba” or Not to “Ba”? LLM Surprisal as a Diagnostic of Context-Sensitive Language Understanding in L2 Chinese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shengjie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Cong</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>Some difficulties in learning Chinese as a second language (L2 Chinese) involve choosing a sentence pattern that is grammatically well formed but less natural in context. Mandarin ba/SVO choice is one such case: learners may avoid ba when the discourse favors it or extend it to contexts where SVO is more appropriate. Because edit-based correction systems may leave both alternatives unchanged, diagnosing these choices requires sensitivity to discourse context, making the task a targeted test of context-sensitive natural language understanding (NLU). Using 200 controlled discourse contexts, we examine whether autoregressive LLM surprisal can serve as a graded diagnostic of this distinction. Across 21 open-weight models, sentence-level mean surprisal identifies the contextually preferred continuation with a mean model-level accuracy of 87.93%, whereas a MacBERT-based correction baseline leaves most contextually non-preferred continuations unchanged. Relevant context generally lowers surprisal for the intended continuation, and sentence-level scoring is more reliable than first-token scoring, whose interpretation varies with tokenizer granularity. The results suggest that surprisal can complement edit-based correction in L2 pragmatic assessment, while cross-model asymmetries, structural preference biases, and tokenizer effects underscore the need for construction-specific controls and human interpretation when evaluating context-sensitive NLU.</abstract>
<identifier type="citekey">zhang-cong-2026-ba</identifier>
<location>
<url>https://aclanthology.org/2026.luhme-1.18/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>227</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To “Ba” or Not to “Ba”? LLM Surprisal as a Diagnostic of Context-Sensitive Language Understanding in L2 Chinese
%A Zhang, Shengjie
%A Cong, Yan
%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-cong-2026-ba
%X Some difficulties in learning Chinese as a second language (L2 Chinese) involve choosing a sentence pattern that is grammatically well formed but less natural in context. Mandarin ba/SVO choice is one such case: learners may avoid ba when the discourse favors it or extend it to contexts where SVO is more appropriate. Because edit-based correction systems may leave both alternatives unchanged, diagnosing these choices requires sensitivity to discourse context, making the task a targeted test of context-sensitive natural language understanding (NLU). Using 200 controlled discourse contexts, we examine whether autoregressive LLM surprisal can serve as a graded diagnostic of this distinction. Across 21 open-weight models, sentence-level mean surprisal identifies the contextually preferred continuation with a mean model-level accuracy of 87.93%, whereas a MacBERT-based correction baseline leaves most contextually non-preferred continuations unchanged. Relevant context generally lowers surprisal for the intended continuation, and sentence-level scoring is more reliable than first-token scoring, whose interpretation varies with tokenizer granularity. The results suggest that surprisal can complement edit-based correction in L2 pragmatic assessment, while cross-model asymmetries, structural preference biases, and tokenizer effects underscore the need for construction-specific controls and human interpretation when evaluating context-sensitive NLU.
%U https://aclanthology.org/2026.luhme-1.18/
%P 227-245
Markdown (Informal)
[To “Ba” or Not to “Ba”? LLM Surprisal as a Diagnostic of Context-Sensitive Language Understanding in L2 Chinese](https://aclanthology.org/2026.luhme-1.18/) (Zhang & Cong, LUHME 2026)
ACL