Back to search

Article

SPS-LIME: Role-Aware Segment Perturbation for Explaining Long Legal Documents

2026-08-14

Abstract excerpt

<title>Abstract</title> <p>Legal text classifiers may achieve strong classification performance, but their practical value depends on whether their decisions can be explained through discourse units that correspond to recognizable forms of legal reasoning. Existing perturbation-based explanation methods commonly operate on individual tokens or sentences, which can fragment factual narratives, party arguments, and...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
b8c12905-174e-58e2-8a4a-344c7e22232b
DOI
10.21203/rs.3.rs-10591506/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
SPS-LIME: Role-Aware Segment Perturbation for Explaining Long Legal DocumentsDOI 10.21203/rs.3.rs-10591506/v1
CASESUMM: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court OpinionsSemantic proximity
Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and StereotypesSemantic proximity
FactLink: A Cross-Domain Benchmark for Link Role Classification for Fact-CheckingSemantic proximity
Private Local Large Language Model for Generating Context-Aware Responses About the Regulations of Book Four of the Civil Code of Catalonia and the Notary Profession of SpainSemantic proximity
From Argumentation to Labeled Logic Program for LLM VerificationSemantic proximity
Synthetic Legal Data Generation for Saudi Family Law Courts Using Multi-Role SimulationSemantic proximity
From Linguistic Rights to Explainable Learning Analytics: A Cross-jurisdictional Policy Framework for Generative AI Feedback in Professional Interpreter EducationSemantic proximity
Context-Grounded Factuality Enhancement in LLM Responses via Multi-Stage Critique and RefinementSemantic proximity
Exploring the Potential of Large Language Models for Counter Argument GenerationSemantic proximity
A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity
A Survey on Hallucination in Large Language and Foundation ModelsSemantic proximity
Exploring Textual Semantics in Large Language ModelsSemantic proximity
Select a neighboring publication to make it the new centre.