critical thinking

This study addresses the challenge of effectively guiding students to transition from misconceptions to accurate causal reasoning within a single classroom session, particularly in engineering fault-diagnosis contexts. It proposes a “detective-style scaffolding instructional framework” that reconfigures classroom voting systems into evidence-centered reasoning probes—rather than mere engagement tools—through three stages: hypothesis activation, evidence structuring, and causal integration. The approach exposes how conventional scoring often misjudges reasoning quality and instead employs dual-precision reasoning analysis to assess learning outcomes. In experiments, 80 third-year polymer engineering students increased their correct identification rate of humidity as the root cause from 29% to 100% within 90 minutes; additionally, 26 high school students without engineering backgrounds achieved 100% accuracy on transfer tasks and demonstrated significantly enhanced confidence in data analysis and ability to interpret AI-generated explanations.

This work investigates large language models’ (LLMs) capabilities in evidence-based claim verification, specifically evaluating deductive versus abductive reasoning. To this end, we introduce RECV—the first benchmark featuring real-world claims with fine-grained, atomic-level annotations of reasoning types—and propose a reasoning-type decomposition evaluation framework. Through systematic assessment of mainstream closed-source LLMs across multiple difficulty levels and prompting strategies, complemented by semantic similarity analysis, we find that: (1) LLMs exhibit robust performance on deductive reasoning but suffer from systematic failures in abductive reasoning; (2) generated explanations achieve high semantic similarity to human-written ones—especially for deductive tasks—but rationalization does not consistently improve verification accuracy. This study provides the first empirical evidence of LLMs’ fundamental limitations in abductive reasoning, establishing a novel, trustworthy benchmark and methodology for rigorous reasoning evaluation.

This study addresses the uncontrolled false positive rates and misleading inferences arising from commonly used simulation methods in shift-share designs. We systematically evaluate prevailing inferential approaches in empirical research through a suite of multilevel simulation experiments. By comparing Monte Carlo analysis with counterfactual data-generating mechanisms, we uncover non-monotonic trade-offs among fidelity, sensitivity, and risk of misdirection across simulation designs. We propose a novel “progressive-fidelity simulation framework,” demonstrating that low-fidelity simulations suffice to expose fundamental inferential flaws, whereas high-fidelity simulations detect subtle, previously overlooked biases—substantially improving detection power. The framework balances interpretability and computational efficiency, offering a reproducible and scalable paradigm for assessing the robustness of causal inference methods.

This study addresses the challenges students face in diagnostic reasoning—particularly susceptibility to cognitive biases such as premature closure and overreliance on heuristics, as well as limited strategy transferability—within a situated learning environment for pharmacy technician training. For the first time, it comparatively examines two theory-driven scaffolding dialogue strategies: structured and problematizing. An intelligent tutoring agent, integrating learning analytics and large language models, dynamically intervenes in learners’ trajectories. Findings indicate that both scaffolding approaches effectively promote the use of diagnostic strategies: structured scaffolding enhances the accuracy of active interaction, while problematizing scaffolding fosters constructive engagement. Notably, task complexity exerts a significantly stronger influence on performance than either prior knowledge or scaffolding type.

This study addresses the narrow scope of purely theory- or data-driven approaches in AI-assisted innovation by proposing the first LLM-based hypothesis generation framework that jointly leverages scholarly literature and empirical data. Methodologically, it introduces a novel dual-source synergy mechanism integrating literature semantic parsing with multi-source data alignment, augmented by domain-specific prompt engineering and rigorous human evaluation. Key contributions include: (1) establishing the first theory- and data-coordinated paradigm for automated hypothesis generation; (2) achieving statistically significant improvements in hypothesis quality—+8.97% over few-shot baselines, +15.75% over literature-only methods, and +3.37% over data-only methods—across five benchmark datasets; and (3) demonstrating via human evaluation that the framework substantially enhances decision-making accuracy in AI-content identification tasks, with gains ranging from 7.44% to 14.19%.

This work addresses the limited interpretability and accountability of large language models (LLMs) in root cause analysis, which hinder their applicability in high-stakes operational settings requiring rigorous evidence chains, hypothesis comparison, and uncertainty handling. The authors propose JustDiag, a diagnostic argumentation engine that introduces, for the first time, an explicit modeling of the diagnostic reasoning process into root cause analysis. JustDiag structures and maintains states such as evidence, findings, competing hypotheses, conflicts, and follow-up checks to enable traceable and auditable inference, complemented by a calibration mechanism that explicitly accounts for uncertainty. Integrating LLMs with a structured reasoning framework, the approach employs a two-tier evaluation protocol to assess both outcome and reasoning quality. Experiments on 66 real-world incidents demonstrate that JustDiag significantly outperforms non-argumentative baselines in both outcome and process scores, exhibiting superior uncertainty retention despite a slightly lower completion rate.

This work addresses the susceptibility of large language models to user-provided incomplete or erroneous assumptions in interactive technical diagnosis, which often leads to confirmation bias. To mitigate this, the authors propose an evidence-first multi-agent framework featuring an “investigator” agent that evaluates question ambiguity, iteratively updates hypothesis probabilities via Bayesian inference, and actively poses clarifying questions—thereby prioritizing evidence-driven reasoning over assumption accommodation. The system integrates a problem-solution extractor, a ground-truth evaluator, and the investigator agent within a structured dialogue framework. Evaluated on technical forums spanning mechanical, electrical, and hydraulic domains, the approach significantly outperforms both direct prompting and pure reasoning baselines, effectively curbing misleading hypothesis adherence and enhancing diagnostic accuracy and robustness.

Existing argument analysis tools struggle to evaluate the conditional validity of arguments across diverse worldviews. This work proposes a multi-perspective reasoning framework that operationalizes conditional validity for the first time by integrating structured worldview modeling, three-tier natural language inference, and conditional reasoning with large language models. The system automatically identifies value conflicts and assumption gaps, generating perspective-specific explanations. It further supports interactive visualization to effectively reveal differences in logical and normative coherence of the same argument under pluralistic value systems, thereby enabling users to explore multidimensional interpretations of complex arguments.

This study addresses a critical yet overlooked limitation in large reasoning models: despite their ability to generate high-quality reasoning chains, they struggle to accurately evaluate the validity of others’ reasoning—a phenomenon termed the “generation-evaluation gap.” To systematically investigate this issue, the authors introduce the VAIR dataset, which probes model judgment in scenarios where answers are correct but underlying reasoning is flawed. Through chain-of-thought analysis, linear probing, and causal intervention techniques, the work reveals that models exhibit more severe evaluation deficits than humans, primarily due to answer confirmation bias rather than insufficient reasoning representation capacity. Experiments show that state-of-the-art models achieve only 48% accuracy on VAIR, starkly contrasting their near-perfect generation performance, and causal interventions confirm that perceived answer correctness overwhelmingly drives their evaluations.

This work addresses the tendency of current AI-driven scientific systems to generate claims that exceed the scope of supporting evidence. It proposes a “claim calibration” framework that models AI-assisted research as an iterative cycle comprising hypothesis generation, consequence derivation, external validation, belief updating, and claim calibration, emphasizing that scientific assertions must be constrained by evidential warrant. The framework distinguishes four semantic forms of claims, defines the claim-evidence gap and associated epistemic debt, and introduces minimal structural revision as a calibration pathway. Validation is demonstrated through multi-agent collaboration paradigms, AI scientist pipelines, and the AISim-Cal synthetic dynamics example. The study establishes three guiding principles—including “no claim without warrant”—to construct an iterative, reliable evaluation loop for trustworthy AI-enabled scientific research.