AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection

TL;DR

This paper introduces a novel agentic LLM pipeline for extracting psycholinguistic conspiracy markers and detecting conspiracy endorsement, employing innovative methods to improve interpretability and performance in NLP tasks.

Contribution

The paper presents a decoupled LLM architecture with DD-CoT and Anti-Echo Chamber components, advancing interpretability and effectiveness in conspiracy detection and marker extraction.

Findings

Achieved 0.24 Macro F1 on S1, doubling baseline performance.

Achieved 0.79 Macro F1 on S2, significantly surpassing previous results.

Ranked 3rd on the development leaderboard for S1.

Abstract

This paper presents a novel agentic LLM pipeline for SemEval-2026 Task 10 that jointly extracts psycholinguistic conspiracy markers and detects conspiracy endorsement. Unlike traditional classifiers that conflate semantic reasoning with structural localization, our decoupled design isolates these challenges. For marker extraction, we propose Dynamic Discriminative Chain-of-Thought (DD-CoT) with deterministic anchoring to resolve semantic ambiguity and character-level brittleness. For conspiracy detection, an "Anti-Echo Chamber" architecture, consisting of an adversarial Parallel Council adjudicated by a Calibrated Judge, overcomes the "Reporter Trap," where models falsely penalize objective reporting. Achieving 0.24 Macro F1 (+100\% over baseline) on S1 and 0.79 Macro F1 (+49\%) on S2, with the S1 system ranking 3rd on the development leaderboard, our approach establishes a versatile paradigm for interpretable, psycholinguistically-grounded NLP.