Unveiling the Mathematical Reasoning in DeepSeek Models: A Comparative Study of Large Language Models

With the rapid evolution of Artificial Intelligence (AI), Large Language Models (LLMs) have reshaped the frontiers of various fields, spanning healthcare, public health, engineering, science, agriculture, education, arts, humanities, and mathematical reasoning. Among these advancements, DeepSeek models have emerged as noteworthy contenders, demonstrating promising capabilities that set them apart from their peers. While previous studies have conducted comparative analyses of LLMs, few have delivered a comprehensive evaluation of mathematical reasoning across a broad spectrum of LLMs. In this work, we aim to bridge this gap by conducting an in-depth comparative study, focusing on the strengths and limitations of DeepSeek models in relation to their leading counterparts. In particular, our study systematically evaluates the mathematical reasoning performance of two DeepSeek models alongside five prominent LLMs across three independent benchmark datasets. The findings reveal several key insights: 1). DeepSeek-R1 consistently achieved the highest accuracy on two of the three datasets, demonstrating strong mathematical reasoning capabilities. 2). The distilled variant of LLMs significantly underperformed compared to its peers, highlighting potential drawbacks in using distillation techniques. 3). In terms of response time, Gemini 2.0 Flash demonstrated the fastest processing speed, outperforming other models in efficiency, which is a crucial factor for real-time applications. Beyond these quantitative assessments, we delve into how architecture, training, and optimization impact LLMs' mathematical reasoning. Moreover, our study goes beyond mere performance comparison by identifying key areas for future advancements in LLM-driven mathematical reasoning. This research enhances our understanding of LLMs' mathematical reasoning and lays the groundwork for future advancements

From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches

Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and systematic comparative analysis, leading to inconsistencies in terminologies and categorizations. Meanwhile, as an increasing number of fine-tuned models are publicly available, their original training data often remain inaccessible due to privacy concerns or intellectual property restrictions. This makes traditional multi-task learning based on shared training data impractical. In scenarios where direct access to training data is infeasible, merging model parameters to create a unified model with broad generalization across multiple domains becomes crucial, further underscoring the importance of model merging techniques. Despite the rapid progress in this field, a comprehensive taxonomy and survey summarizing recent advances and predicting future directions are still lacking. This paper addresses these gaps by establishing a new taxonomy of model merging methods, systematically comparing different approaches, and providing an overview of key developments. By offering a structured perspective on this evolving area, we aim to help newcomers quickly grasp the field's landscape and inspire further innovations.

A Survey on Post-training of Large Language Models

The emergence of Large Language Models (LLMs) has fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration. However, their pre-trained architectures often reveal limitations in specialized contexts, including restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance. These challenges necessitate advanced post-training language models (PoLMs) to address these shortcomings, such as OpenAI-o1/o3 and DeepSeek-R1 (collectively known as Large Reasoning Models, or LRMs). This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Efficiency, which optimizes resource utilization amidst increasing complexity; and Integration and Adaptation, which extend capabilities across diverse modalities while addressing coherence issues. Charting progress from ChatGPT's foundational alignment strategies to DeepSeek-R1's innovative reasoning advancements, we illustrate how PoLMs leverage datasets to mitigate biases, deepen reasoning capabilities, and enhance domain adaptability. Our contributions include a pioneering synthesis of PoLM evolution, a structured taxonomy categorizing techniques and datasets, and a strategic agenda emphasizing the role of LRMs in improving reasoning proficiency and domain flexibility. As the first survey of its scope, this work consolidates recent PoLM advancements and establishes a rigorous intellectual framework for future research, fostering the development of LLMs that excel in precision, ethical robustness, and versatility across scientific and societal applications.

A Practical Memory Injection Attack against LLM Agents

Agents based on large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised memory bank may easily produce harmful outputs when the past records retrieved for demonstration are malicious. In this paper, we propose a novel Memory INJection Attack, MINJA, that enables the injection of malicious records into the memory bank by only interacting with the agent via queries and output observations. These malicious records are designed to elicit a sequence of malicious reasoning steps leading to undesirable agent actions when executing the victim user's query. Specifically, we introduce a sequence of bridging steps to link the victim query to the malicious reasoning steps. During the injection of the malicious record, we propose an indication prompt to guide the agent to autonomously generate our designed bridging steps. We also propose a progressive shortening strategy that gradually removes the indication prompt, such that the malicious record will be easily retrieved when processing the victim query comes after. Our extensive experiments across diverse agents demonstrate the effectiveness of MINJA in compromising agent memory. With minimal requirements for execution, MINJA enables any user to influence agent memory, highlighting practical risks of LLM agents.

SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?

Large Language Models (LLMs) have shown remarkable capabilities in general domains but often struggle with tasks requiring specialized knowledge. Conventional Retrieval-Augmented Generation (RAG) techniques typically retrieve external information from static knowledge bases, which can be outdated or incomplete, missing fine-grained clinical details essential for accurate medical question answering. In this work, we propose SearchRAG, a novel framework that overcomes these limitations by leveraging real-time search engines. Our method employs synthetic query generation to convert complex medical questions into search-engine-friendly queries and utilizes uncertainty-based knowledge selection to filter and incorporate the most relevant and informative medical knowledge into the LLM's input. Experimental results demonstrate that our method significantly improves response accuracy in medical question answering tasks, particularly for complex questions requiring detailed and up-to-date knowledge.

Fine-Tuning Open-Source Large Language Models to Improve Their Performance on Radiation Oncology Tasks: A Feasibility Study to Investigate Their Potential Clinical Applications in Radiation Oncology

Background: The radiation oncology clinical practice involves many steps relying on the dynamic interplay of abundant text data. Large language models have displayed remarkable capabilities in processing complex text information. But their direct applications in specific fields like radiation oncology remain underexplored. Purpose: This study aims to investigate whether fine-tuning LLMs with domain knowledge can improve the performance on Task (1) treatment regimen generation, Task (2) treatment modality selection (photon, proton, electron, or brachytherapy), and Task (3) ICD-10 code prediction in radiation oncology. Methods: Data for 15,724 patient cases were extracted. Cases where patients had a single diagnostic record, and a clearly identifiable primary treatment plan were selected for preprocessing and manual annotation to have 7,903 cases of the patient diagnosis, treatment plan, treatment modality, and ICD-10 code. Each case was used to construct a pair consisting of patient diagnostics details and an answer (treatment regimen, treatment modality, or ICD-10 code respectively) for the supervised fine-tuning of these three tasks. Open source LLaMA2-7B and Mistral-7B models were utilized for the fine-tuning with the Low-Rank Approximations method. Accuracy and ROUGE-1 score were reported for the fine-tuned models and original models. Clinical evaluation was performed on Task (1) by radiation oncologists, while precision, recall, and F-1 score were evaluated for Task (2) and (3). One-sided Wilcoxon signed-rank tests were used to statistically analyze the results. Results: Fine-tuned LLMs outperformed original LLMs across all tasks with p-value <= 0.001. Clinical evaluation demonstrated that over 60% of the fine-tuned LLMs-generated treatment regimens were clinically acceptable. Precision, recall, and F1-score showed improved performance of fine-tuned LLMs.

Brain-Adapter: Enhancing Neurological Disorder Analysis with Adapter-Tuning Multimodal Large Language Models

Understanding brain disorders is crucial for accurate clinical diagnosis and treatment. Recent advances in Multimodal Large Language Models (MLLMs) offer a promising approach to interpreting medical images with the support of text descriptions. However, previous research has primarily focused on 2D medical images, leaving richer spatial information of 3D images under-explored, and single-modality-based methods are limited by overlooking the critical clinical information contained in other modalities. To address this issue, this paper proposes Brain-Adapter, a novel approach that incorporates an extra bottleneck layer to learn new knowledge and instill it into the original pre-trained knowledge. The major idea is to incorporate a lightweight bottleneck layer to train fewer parameters while capturing essential information and utilize a Contrastive Language-Image Pre-training (CLIP) strategy to align multimodal data within a unified representation space. Extensive experiments demonstrated the effectiveness of our approach in integrating multimodal data to significantly improve the diagnosis accuracy without high computational costs, highlighting the potential to enhance real-world diagnostic workflows.

Classification of Mild Cognitive Impairment Based on Dynamic Functional Connectivity Using Spatio-Temporal Transformer

Dynamic functional connectivity (dFC) using resting-state functional magnetic resonance imaging (rs-fMRI) is an advanced technique for capturing the dynamic changes of neural activities, and can be very useful in the studies of brain diseases such as Alzheimer's disease (AD). Yet, existing studies have not fully leveraged the sequential information embedded within dFC that can potentially provide valuable information when identifying brain conditions. In this paper, we propose a novel framework that jointly learns the embedding of both spatial and temporal information within dFC based on the transformer architecture. Specifically, we first construct dFC networks from rs-fMRI data through a sliding window strategy. Then, we simultaneously employ a temporal block and a spatial block to capture higher-order representations of dynamic spatio-temporal dependencies, via mapping them into an efficient fused feature representation. To further enhance the robustness of these feature representations by reducing the dependency on labeled data, we also introduce a contrastive learning strategy to manipulate different brain states. Experimental results on 345 subjects with 570 scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate the superiority of our proposed method for MCI (Mild Cognitive Impairment, the prodromal stage of AD) prediction, highlighting its potential for early identification of AD.

Large Language Models for Bioinformatics

With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options

Purpose: We present an updated study evaluating the performance of large language models (LLMs) in answering radiation oncology physics questions, focusing on the latest released models. Methods: A set of 100 multiple-choice radiation oncology physics questions, previously created by us, was used for this study. The answer options of the questions were randomly shuffled to create "new" exam sets. Five LLMs -- OpenAI o1-preview, GPT-4o, LLaMA 3.1 (405B), Gemini 1.5 Pro, and Claude 3.5 Sonnet -- with the versions released before September 30, 2024, were queried using these new exams. To evaluate their deductive reasoning abilities, the correct answer options in the questions were replaced with "None of the above." Then, the explain-first and step-by-step instruction prompt was used to test if it improved their reasoning abilities. The performance of the LLMs was compared to medical physicists in majority-vote scenarios. Results: All models demonstrated expert-level performance on these questions, with o1-preview even surpassing medical physicists in majority-vote scenarios. When substituting the correct answer options with "None of the above," all models exhibited a considerable decline in performance, suggesting room for improvement. The explain-first and step-by-step instruction prompt helped enhance the reasoning abilities of LLaMA 3.1 (405B), Gemini 1.5 Pro, and Claude 3.5 Sonnet models. Conclusion: These latest LLMs demonstrated expert-level performance in answering radiation oncology physics questions, exhibiting great potential for assisting in radiation oncology physics education.