We present Spoiler Court, a multi-agent adversarial framework for interpretable spoiler detection in movie reviews. Three LLM agents, acting as the Plaintiff, Defendant, and Judge, engage in a multi-round courtroom debate to identify spoiler spans, challenge them, and deliver a final judgement with an interpretable audit trail grounded in the movie’s plot summary. Unlike prior work that produces only binary labels, Spoiler Court outputs which sentences are spoilers, why (via plot fact citations), and how the decision was reached (via adversarial debate transcripts). To evaluate the effectiveness of our approach, we construct a multi-genre evaluation dataset spanning 4 movies with binary and character-level span annotations. Under controlled conditions, Spoiler Court achieves an average F1 of 0.733 across 4 movies, outperforming other baselines including a dedicated spoiler detection framework.

Scope ambiguity arises when a single surface string admits multiple logical interpretations depending on how operators such as negation and indefinites interact. Prior work (Kamath et al. 2024) primarily evaluates scope sensitivity through output-level behavior, leaving open whether alternative interpretations are internally represented or merely reflected in shifted token probabilities.

We introduce **an evidence-first, ambiguity-following diagnostic** that asks a more specific question: when the surface string is held constant and only contextual evidence biases interpretation, do transformer language models form distinct internal representations corresponding to alternative logical readings?

To investigate this, we present **SCOPEx**, extending the dataset of Kamath et al. (2024) by systematically manipulating preceding context while keeping the ambiguous sentence identical. We further introduce passivized variants as syntactically less ambiguous controls. Using SCOPEx, we show that transformer LMs:

(i) exhibit **systematic scope-sensitive behavior conditioned on context**, and

(ii) form **separable hidden-state representations for alternative scope readings of the same surface string**.

This divergence emerges in later layers and causally influences downstream predictions.