AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection
This work addresses the problem of accurately identifying psycholinguistic markers and detecting conspiracy endorsement for researchers and platforms combating misinformation, offering significant performance gains over baselines.
This paper introduces an agentic LLM pipeline for SemEval-2026 Task 10, designed to extract psycholinguistic conspiracy markers and detect conspiracy endorsement. The system achieved a 0.24 Macro F1 on S1, representing a 100% improvement over the baseline, and 0.79 Macro F1 on S2, a 49% improvement.
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.