arXiv:2606. 15127v1 Announce Type: new Abstract: Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input.
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
arXiv:2607. 26102v1 Announce Type: cross Abstract: Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference.
arXiv:2603. 05167v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility.
arXiv:2606. 24839v1 Announce Type: new Abstract: Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics.
arXiv:2606. 10296v1 Announce Type: cross Abstract: Multi-agent debate systems are typically evaluated only on whether the final answer is correct, overlooking the quality of the intermediate reasoning that debate is designed to produce.
arXiv:2607. 08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise.
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
arXiv:2607. 01223v1 Announce Type: new Abstract: When should an AI system's answer be trusted?
arXiv:2606. 01462v1 Announce Type: new Abstract: Studies of human reasoning have shown that people are typically stronger at evaluating reasoning than producing it from scratch.
arXiv:2603. 25251v2 Announce Type: replace-cross Abstract: Explainable AI (XAI) methods are commonly evaluated using functional correctness metrics, sometimes termed faithfulness or fidelity, which estimate how closely an explanation reflects the model's reasoning.
arXiv:2607. 25634v1 Announce Type: new Abstract: We present AIriskEval-edu Demo, a platform that audits the pedagogical quality of instructional explanations and provides explainable audit results.