@inproceedings{banerjee-etal-2026-lost,
title = "Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations",
author = "Banerjee, Somnath and
Jha, Pranav and
Hazra, Rima and
Mukherjee, Animesh",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2289/",
pages = "52077--52101",
ISBN = "979-8-89176-459-0",
abstract = "LLMs deployed multilingually are often audited via English explanations for non-English inputs. We evaluate extractive explanations ``where the model identifies input token spans as evidence alongside a generated rationale'' and uncover a systematic trade-off: English-pivot explanations can achieve higher span agreement with human rationales while their evidence becomes less causally grounded in the model{'}s prediction, as measured by both comprehensiveness and sufficiency. Across 3 tasks, 5 languages, and 2 multilingual LLM families, we find that English explanations frequently produce fluent but loosely anchored rationales, with comprehensiveness degrading by up to 5.7x relative to native-language conditions - even as task accuracy remains stable across settings. For socially nuanced classification, English pivots also fail to preserve pragmatic cues, reducing both faithfulness and span agreement. We recommend auditing explanations in the input language, reporting multi-faceted faithfulness metrics beyond lexical overlap, and treating English rationales as communication summaries rather than faithful decision traces."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-etal-2026-lost">
<titleInfo>
<title>Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Somnath</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Jha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rima</namePart>
<namePart type="family">Hazra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="family">Mukherjee</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>LLMs deployed multilingually are often audited via English explanations for non-English inputs. We evaluate extractive explanations “where the model identifies input token spans as evidence alongside a generated rationale” and uncover a systematic trade-off: English-pivot explanations can achieve higher span agreement with human rationales while their evidence becomes less causally grounded in the model’s prediction, as measured by both comprehensiveness and sufficiency. Across 3 tasks, 5 languages, and 2 multilingual LLM families, we find that English explanations frequently produce fluent but loosely anchored rationales, with comprehensiveness degrading by up to 5.7x relative to native-language conditions - even as task accuracy remains stable across settings. For socially nuanced classification, English pivots also fail to preserve pragmatic cues, reducing both faithfulness and span agreement. We recommend auditing explanations in the input language, reporting multi-faceted faithfulness metrics beyond lexical overlap, and treating English rationales as communication summaries rather than faithful decision traces.</abstract>
<identifier type="citekey">banerjee-etal-2026-lost</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2289/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52077</start>
<end>52101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations
%A Banerjee, Somnath
%A Jha, Pranav
%A Hazra, Rima
%A Mukherjee, Animesh
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F banerjee-etal-2026-lost
%X LLMs deployed multilingually are often audited via English explanations for non-English inputs. We evaluate extractive explanations “where the model identifies input token spans as evidence alongside a generated rationale” and uncover a systematic trade-off: English-pivot explanations can achieve higher span agreement with human rationales while their evidence becomes less causally grounded in the model’s prediction, as measured by both comprehensiveness and sufficiency. Across 3 tasks, 5 languages, and 2 multilingual LLM families, we find that English explanations frequently produce fluent but loosely anchored rationales, with comprehensiveness degrading by up to 5.7x relative to native-language conditions - even as task accuracy remains stable across settings. For socially nuanced classification, English pivots also fail to preserve pragmatic cues, reducing both faithfulness and span agreement. We recommend auditing explanations in the input language, reporting multi-faceted faithfulness metrics beyond lexical overlap, and treating English rationales as communication summaries rather than faithful decision traces.
%U https://aclanthology.org/2026.emnlp-main.2289/
%P 52077-52101
Markdown (Informal)
[Lost in Interpretation: The Plausibility-Faithfulness Trade-off in Cross-Lingual Explanations](https://aclanthology.org/2026.emnlp-main.2289/) (Banerjee et al., EMNLP 2026)
ACL