CUET_Luminaries at SemEval-2026 Task 11: Disentangling Logical Validity from Semantic Plausibility through Canonical Abstraction

Validity-Aware Jailbreak Evaluation for Large Language Models

This work proposes Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness, and shows that enforcing correctness substantially reshapes measured robustness.

Do Language Models Know What Words Mean? Evaluating Semantic Knowledge of Adjective-Noun Compounds

Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning

The findings relocate the bottleneck of commonsense reasoning failures from model competence to elicitation, and release SaliTrap as a testbed for this blind spot, to show that lightweight, inference-time prompting alone substantially closes the gap without any retraining.

Multi-Criteria Evaluation of Hierarchical Reasoning, Self-Correction, and Factual Consistency in Large Language Models across Complex Language Tasks

This paper introduces a comprehensive multi-criteria evaluation methodology designed to assess the capabilities of these advanced computational architectures in handling complex language tasks, focusing on three foundational dimensions: hierarchical reasoning, self-correction mechanisms, and factual consistency.

Evaluating Trustworthy Multilingual Alignment in LLMs via Synthetic Natural Language Inference

A controlled evaluation framework for multilingual natural language inference that stress-tests semantic consistency using synthetic logic-based premise–hypothesis pairs in both monolingual and code-switched conditions is presented.

Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

This work operationalizes the importance of a reasoning step as its advantage: the change in expected reward, e.g., producing the correct final answer, from including that step, estimated via Monte Carlo rollouts, and evaluates whether LLM judges can identify high-advantage steps and finds that sufficiently capable LLM...