<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sadhu-etal-2026-cited">
    <titleInfo>
        <title>Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Saisab</namePart>
        <namePart type="family">Sadhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shreeyans</namePart>
        <namePart type="family">Arora</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pratinav</namePart>
        <namePart type="family">Seth</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 Natural Legal Language Processing Workshop 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nikolaos</namePart>
            <namePart type="family">Aletras</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ilias</namePart>
            <namePart type="family">Chalkidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leslie</namePart>
            <namePart type="family">Barrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Cătălina</namePart>
            <namePart type="family">Goanță</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoțiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gerasimos</namePart>
            <namePart type="family">Spanakis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shanshan</namePart>
            <namePart type="family">Xu</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">979-8-89176-494-1</identifier>
    </relatedItem>
    <abstract>Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence the decision follows from it. We test this directly: holding case facts fixed, we substitute the named legal authority for an unrelated one and decode a model’s evolving verdict from its hidden states. Across seven open-weight models (8B–70B) and four benchmarks spanning judicial and contractual reasoning, when explicitly required to justify a verdict by naming the governing authority, models name the correct one in 66.7%–100% of generations, while the verdict changing when the authority changes is far less consistent: 0.0%–21.7% on CaseHOLD, 30.0%–76.7% on ECHR and SCOTUS, and 43.3%–50.0% on ContractNLI. Neither scale nor a purpose-built legal-reasoning model (a best-effort LoRA reproduction; Section 6) closes this gap. A red-teaming evaluation on five core models finds compliance with an adversarial instruction hidden in the case facts (73.3%–96.4%) exceeds verdict-swap sensitivity by a wide margin, holding without exception regardless of cross-model ranking. Naming a legal authority is thus a poor proxy for a verdict’s dependence on it, and the same verdict remains separately vulnerable to adversarial manipulation; both findings replicate across checks ruling out prompt-wording noise and confounded sampling, and bear directly on using generated legal explanations as compliance or audit artefacts.</abstract>
    <identifier type="citekey">sadhu-etal-2026-cited</identifier>
    <location>
        <url>https://aclanthology.org/2026.nllp-1.42/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>508</start>
            <end>523</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness
%A Sadhu, Saisab
%A Arora, Shreeyans
%A Seth, Pratinav
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F sadhu-etal-2026-cited
%X Large language models increasingly justify legal decisions by naming the statute or precedent behind a verdict, treated as evidence the decision follows from it. We test this directly: holding case facts fixed, we substitute the named legal authority for an unrelated one and decode a model’s evolving verdict from its hidden states. Across seven open-weight models (8B–70B) and four benchmarks spanning judicial and contractual reasoning, when explicitly required to justify a verdict by naming the governing authority, models name the correct one in 66.7%–100% of generations, while the verdict changing when the authority changes is far less consistent: 0.0%–21.7% on CaseHOLD, 30.0%–76.7% on ECHR and SCOTUS, and 43.3%–50.0% on ContractNLI. Neither scale nor a purpose-built legal-reasoning model (a best-effort LoRA reproduction; Section 6) closes this gap. A red-teaming evaluation on five core models finds compliance with an adversarial instruction hidden in the case facts (73.3%–96.4%) exceeds verdict-swap sensitivity by a wide margin, holding without exception regardless of cross-model ranking. Naming a legal authority is thus a poor proxy for a verdict’s dependence on it, and the same verdict remains separately vulnerable to adversarial manipulation; both findings replicate across checks ruling out prompt-wording noise and confounded sampling, and bear directly on using generated legal explanations as compliance or audit artefacts.
%U https://aclanthology.org/2026.nllp-1.42/
%P 508-523

Markdown (Informal)

[Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness](https://aclanthology.org/2026.nllp-1.42/) (Sadhu et al., NLLP 2026)

• Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness (Sadhu et al., NLLP 2026)

ACL

• Saisab Sadhu, Shreeyans Arora, and Pratinav Seth. 2026. Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness. In Proceedings of the Natural Legal Language Processing Workshop 2026, pages 508–523, Budapest, Hungary. Association for Computational Linguistics.