d-itlab at SemEval-2026 Task 12: Per-Option Surprisal and Multi-Stage Gating for Precision-Oriented Causal Reasoning
Year: 2026
Type: conference-paper
Abstract: We describe the system submitted by d-itlab to SemEval-2026 Task 12 (Abductive Event Reasoning), which requires selecting the most plausible direct cause(s) of an observed event from candidate options grounded in reference documents.Our approach combines (i) peroption multi-stage LLM inference that evaluates each option independently with progressively stricter verification, (ii) surprisal-based features obtained by teacher-forcing candidate sentences and measuring token-level negative log-likelihood, and (iii) an XGBoost ensemble trained on these heterogeneous features to produce a precision-oriented final prediction.In the official test set, our system scored 0.91, ranking third among 116 participating teams.
Authors: Yasunori Terao, Yuuki Tachioka
Institutions: Denso IT Laboratory Inc. (Japan), Denso (United States)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166884896