Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the underlying computations, rather than post-hoc narratives shaped by hints that function as answer shortcuts embedded in the prompt? Following prior work on hinted vs.\ unhinted prompting, we present a systematic study of CoT faithfulness under controlled hint manipulations. Our experimental design spans four datasets (AIME, GSM-Hard, MATH-500, UniADILR), two state-of-the-art models (GPT-4o and Gemini-2-Flash), and a structured set of hint conditions varying in correctness (correct and incorrect), presentation style (sycophancy and data leak), and complexity (raw answers, two-operator expressions, four-operator expressions). We evaluate both task accuracy and whether hints are explicitly acknowledged in the reasoning. Our results reveal three key findings. First, correct hints substantially improve accuracy, especially on harder benchmarks and logical reasoning, while incorrect hints sharply reduce accuracy in tasks with lower baseline competence. Second, acknowledgement of hints is highly uneven: equation-based hints are frequently referenced, whereas raw hints are often adopted silently, indicating that more complex hints push models toward verbalizing their reliance in the reasoning process. Third, presentation style matters: sycophancy prompts encourage overt acknowledgement, while leak-style prompts increase accuracy but promote hidden reliance. This may reflect RLHF-related effects, as sycophancy exploits the human-pleasing side and data leak triggers the self-censoring side. Together, these results demonstrate that LLM reasoning is systematically shaped by shortcuts in ways that obscure faithfulness.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare seven public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting regime for medical question-answering (QA) tasks. For instance, across the tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 12.1% of cases, reach a (statistical) tie in 49.8% of cases, and are significantly worse than their base models in the remaining 38.2% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare ten public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting and supervised fine-tuning regimes for medical question-answering (QA). For instance, across all tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 22.7% of cases, reach a (statistical) tie in 36.8% of cases, and are significantly worse than their base models in the remaining 40.5% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately in zero-/few-shot prompting; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Meanwhile, we find that after fine-tuning on specific QA tasks, medical LLMs can show performance improvements, but the benefits do not carry over to tasks based on clinical notes. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies.

Despite the acknowledged capability of template-free models in exploring unseen reaction spaces compared to template-based models for retrosynthesis prediction, their ability to venture beyond established boundaries remains relatively uncharted. In this study, we empirically assess the extrapolation capability of state-of-the-art template-free models by meticulously assembling an extensive set of out-of-distribution (OOD) reactions. Our findings demonstrate that while template-free models exhibit potential in predicting precursors with novel synthesis rules, their top-10 exact-match accuracy in OOD reactions is strikingly modest (< 1%). Furthermore, despite the capability of generating novel reactions, our investigation highlights a recurring issue where more than half of the novel reactions predicted by template-free models are chemically implausible. Consequently, we advocate for the future development of template-free models that integrate considerations of chemical feasibility when navigating unexplored regions of reaction space.