mlsanityData to 14 Oct 2026

AILS-NTUA at SemEval-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning

arXiv 2603.04319 ↗First posted 4 Mar 2026cs.CLcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

We present a winning three-stage system for SemEval 2026 Task~12: Abductive Event Reasoning that combines graph-based retrieval, LLM-driven abductive reasoning with prompt design optimized through reflective prompt evolution, and post-hoc consistency enforcement; our system ranks first on the evaluation-phase leaderboard with an accuracy score of 0.95. Cross-model error analysis across 14 models (7~families) reveals three shared inductive biases: causal chain incompleteness, proximate cause preference, and salience bias, whose cross-family convergence (51% cause-count reduction) indicates systematic rather than model-specific failure modes in multi-label causal reasoning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 14 of its 40 references that are in the map. First posted on arXiv 4 Mar 2026.

Builds on

14 of 40 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models10 Dec
  2. 2025GEAR: A General Evaluation Framework for Abductive Reasoning28 Sep
  3. 2025Logical Reasoning in Large Language Models: A Survey13 Feb
  4. 2024IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs9 Sep
  5. 2023Abductive Reasoning with the GPT-4 Language Model: Case studies from criminal investigation, medical practice, scientific research17 Jul
  6. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov

Other references · 8

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  4. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  5. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 542
  6. 2023Retrieval meets Long Context Large Language Modelscited by 115
  7. 2024A Comprehensive Evaluation of Large Language Models on Temporal Event Forecastingcited by 8
  8. 2025Event Extraction in Large Language Modelcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMscited by 5
  2. 2026SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs
  2. 2026Graph of States: Solving Abductive Tasks with Large Language Models
  3. 2025Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premises
  4. 2025TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
  5. 2022AbductionRules: Training Transformers to Explain Unexpected Inputs
  6. 2026Abductive Reasoning with Syllogistic Forms in Large Language Models
  7. 2026LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos
  8. 2025Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM