AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection
On the map: LLM agents and tool use → Medical and scientific domain agents
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 66 references that are in the map. First posted on arXiv 5 Mar 2026.
Builds on
17 of 66 references.
References · 17
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
- 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
- 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
- 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 449
- 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 107
- 2024Why Do Large Language Models (LLMs) Struggle to Count Letters?cited by 37
- 2020An automated pipeline for the discovery of conspiracy and conspiracy theory narrative frameworks: Bridgegate, Pizzagate and storytelling on the webcited by 16
- 2023YouNICon: YouTube's CommuNIty of Conspiracy Videoscited by 13
- 2025Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendationscited by 10
5 more
- 2025Unveiling Confirmation Bias in Chain-of-Thought Reasoningcited by 10
- 2025Hallucinated Span Detection with Multi-View Attention Featurescited by 6
- 2024Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connectionscited by 5
- 2024Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Modelscited by 4
- 2025XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocolscited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning
- 2025Detecting Sleeper Agents in Large Language Models via Semantic Drift Analysis
- 2025SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Models
- 2026The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
- 2026MALicious INTent Dataset and Inoculating LLMs for Enhanced Disinformation Detection
- 2025Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
- 2025SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detection
- 2026Agentic Detection of Online Conspiracies