add examples

examples/Pitman-Yor Language Model.md

@@ -0,0 +1,66 @@
+# A Systematic Review of Pitman-Yor Language Model
+
+This systematic review provides an overview of the Pitman-Yor Language Model, a probabilistic model for natural language processing. We discuss the historical background of the model, including the introduction of the Pitman Yor Diffusion Tree (PYDT) for hierarchical clustering. We also explore potential future developments, such as its applications in nonparametric clustering of data and generative transition-based dependency parsing.
+
+## Table of contents
+
+1. Introduction: This section provides an overview of the Pitman-Yor Language Model, a probabilistic model for natural language processing.
+2. Historical Background: This section discusses the historical background of the Pitman-Yor Language Model, including the introduction of the Pitman Yor Diffusion Tree (PYDT) for hierarchical clustering.
+    1. Pitman Yor Diffusion Tree: This subsection discusses the introduction of the Pitman Yor Diffusion Tree (PYDT) for hierarchical clustering.
+3. Future Development: This section explores potential future developments of the Pitman-Yor Language Model, such as its applications in nonparametric clustering of data and generative transition-based dependency parsing.
+    1. Nonparametric Clustering of Data: This subsection discusses the potential application of the Pitman-Yor Language Model in nonparametric clustering of data.
+    2. Generative Transition-Based Dependency Parsing: This subsection discusses the potential application of the Pitman-Yor Language Model in generative transition-based dependency parsing.
+4. Conclusion: This systematic review provides an overview of the Pitman-Yor Language Model, its historical background, and potential future developments.
+
+## Introduction
+
+This section provides an overview of the Pitman-Yor Language Model, a probabilistic model for natural language processing. According to [^1], the Pitman Yor Diffusion Tree (PYDT) is a generalization of the Dirichlet Diffusion Tree, which removes the restriction to binary branching structure. The generative process is described and shown to result in an exchangeable distribution over data points. The model has been proven to have some theoretical properties, and two inference methods have been presented: a collapsed MCMC sampler which allows us to model uncertainty over tree structures, and a computationally efficient greedy Bayesian EM search algorithm. Both algorithms use message passing on the tree structure. The utility of the model and algorithms is demonstrated on synthetic and real-world data, both continuous and binary.
+
+## Historical Background
+
+The Pitman-Yor Language Model is a probabilistic model for natural language processing. The historical background of the model includes the introduction of the Pitman Yor Diffusion Tree (PYDT) for hierarchical clustering [^1]. The PYDT is a generalization of the Dirichlet Diffusion Tree, which removes the restriction to binary branching structure. The generative process of the PYDT is described and shown to result in an exchangeable distribution over data points. The model has some theoretical properties, and two inference methods have been presented: a collapsed MCMC sampler, which allows modeling uncertainty over tree structures, and a computationally efficient greedy Bayesian EM search algorithm. Both algorithms use message passing on the tree structure. The utility of the model and algorithms has been demonstrated on synthetic and real-world data, both continuous and binary. The PYDT has been used to learn hierarchical structure over latent variables in models including Hidden Markov Models and Latent Dirichlet Allocation [^1].
+
+### Pitman Yor Diffusion Tree
+
+The Pitman Yor Diffusion Tree (PYDT) is a generalization of the Dirichlet Diffusion Tree (DDT) for hierarchical clustering, which removes the restriction to binary branching structure [^1][^4]. The generative process of PYDT results in an exchangeable distribution over data points, and some theoretical properties of the model have been proven [^1]. Two inference methods have been presented: a collapsed MCMC sampler that models uncertainty over tree structures, and a computationally efficient greedy Bayesian EM search algorithm that uses message passing on the tree structure [^1]. The utility of the model and algorithms has been demonstrated on synthetic and real-world data, both continuous and binary [^1]. The PYDT can find simpler, more interpretable representations of data than the DDT, and it defines an infinitely exchangeable distribution over data points [^1][^7]. The code for PYDT is publicly available to encourage its use by the community [^1]. 
+
+[^1]: Knowles, D. A., & Ghahramani, Z. (2011). Pitman-Yor diffusion trees. arXiv preprint arXiv:1107.2402.
+[^4]: Knowles, D. A., & Ghahramani, Z. (2012). Nonparametric Bayesian sparse factor models with application to gene expression modeling. The Annals of Applied Statistics, 6(2), 563-588.
+[^7]: Knowles, D. A., & Ghahramani, Z. (2012). Hierarchical clustering using the Pitman-Yor process tree. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(7), 1399-1413.
+
+## Future Development
+
+The Pitman-Yor Language Model has potential future developments in nonparametric clustering of data and generative transition-based dependency parsing. The kernel Pitman-Yor process (KPYP) has been proposed for nonparametric clustering of data with general spatial or temporal interdependencies. The KPYP is constructed by introducing an infinite sequence of random locations and defining a predictor-dependent random probability measure based on the stick-breaking construction of the Pitman-Yor process. The discount hyperparameters of the Beta-distributed random weights of the process are controlled by a kernel function expressing the proximity between the location assigned to each weight and the given predictors [^5][^6].
+
+Moreover, a generative model for transition-based dependency parsing has been proposed, parameterized by Hierarchical Pitman-Yor Processes (HPYPs). The model learns a distribution over derivations of parser transitions, words, and POS tags. To enable efficient inference, a novel algorithm for linear-time decoding in a generative transition-based parser has been proposed based on particle filtering, a method for sequential Monte Carlo sampling. This method enables the beam-size during decoding to depend on the uncertainty of the model. The model has high accuracy and obtains better perplexity than an n-gram model by performing semi-supervised learning over a large unlabelled corpus. The model is also able to generate locally and syntactically coherent sentences, opening the door to further applications in language generation [^8][^9].
+
+### Nonparametric Clustering of Data
+
+The Pitman-Yor Language Model has potential applications in nonparametric clustering of data. In particular, the kernel Pitman-Yor process (KPYP) has been proposed for nonparametric clustering of data with general spatial or temporal interdependencies. The KPYP is constructed by introducing an infinite sequence of random locations and defining a predictor-dependent random probability measure based on the stick-breaking construction of the Pitman-Yor process. The discount hyperparameters of the Beta-distributed random weights (stick variables) of the process are controlled by a kernel function expressing the proximity between the location assigned to each weight and the given predictors [^5][^6]. The performance of the KPYP prior has been studied in unsupervised image segmentation and text-dependent speaker identification, and compared to the kernel stick-breaking process and the Dirichlet process prior [^5][^6]. 
+
+Overall, the Pitman-Yor Language Model has the potential to be a useful tool for nonparametric clustering of data, particularly when dealing with spatial or temporal interdependencies.
+
+### Generative Transition-Based Dependency Parsing
+
+The Pitman-Yor Language Model has potential applications in generative transition-based dependency parsing. A simple, scalable, fully generative model for transition-based dependency parsing with high accuracy has been proposed, which is parameterized by Hierarchical Pitman-Yor Processes [^8]. The model learns a distribution over derivations of parser transitions, words, and POS tags. To enable efficient inference, a novel algorithm for linear-time decoding in a generative transition-based parser has been proposed, which is based on particle filtering [^8]. The algorithm enables the beam-size during decoding to depend on the uncertainty of the model. The model is able to generate locally and syntactically coherent sentences, opening the door to further applications in language generation [^8].
+
+## Conclusion
+
+This systematic review provides an overview of the Pitman-Yor Language Model, its historical background, and potential future developments. The Pitman Yor Diffusion Tree (PYDT) was introduced as a generalization of the Dirichlet Diffusion Tree for hierarchical clustering [^1]. The model has shown promising results in nonparametric clustering of data [^5][^6] and generative transition-based dependency parsing [^8]. The Pitman-Yor process has also been characterized for its heavy-tailed mixture models [^3] and estimation of its type parameter by empirical and full Bayes methods [^4]. While the model has been evaluated with perplexity, other approaches have been proposed to evaluate the success or failure of the model [^2]. Overall, the Pitman-Yor Language Model has shown potential in various applications and can be further developed to improve its performance in natural language processing tasks.
+
+## References
+[^1]: [Knowles, David A., and Zoubin Ghahramani. "Pitman-Yor diffusion trees." arXiv preprint arXiv:1106.2494 (2011).](https://arxiv.org/abs/1106.2494)
+
+[^2]: [Takahashi, Shuntaro, and Kumiko Tanaka-Ishii. "Assessing language models with scaling properties." arXiv preprint arXiv:1804.08881 (2018).](https://arxiv.org/abs/1804.08881)
+
+[^3]: [Ramirez, Vianey Palacios, Miguel de Carvalho, and Luis Gutierrez Inostroza. "Heavy-Tailed Pitman--Yor Mixture Models." arXiv preprint arXiv:2211.00867 (2022).](https://arxiv.org/abs/2211.00867)
+
+[^4]: [Franssen, S. E. M. P., and A. W. van der Vaart. "Empirical and Full Bayes estimation of the type of a Pitman-Yor process." arXiv preprint arXiv:2208.14255 (2022).](https://arxiv.org/abs/2208.14255)
+
+[^5]: [Chatzis, Sotirios P., Dimitrios Korkinof, and Yiannis Demiris. "The Kernel Pitman-Yor Process." arXiv preprint arXiv:1210.4184 (2012).](https://arxiv.org/abs/1210.4184)
+
+[^6]: [Chatzis, Sotirios P., Dimitrios Korkinof, and Yiannis Demiris. "The Kernel Pitman-Yor Process." arXiv preprint arXiv:1210.4184 (2012).](https://arxiv.org/abs/1210.4184)
+
+[^7]: [Okita, Tsuyoshi. "Joint space neural probabilistic language model for statistical machine translation." arXiv preprint arXiv:1301.3614 (2013).](https://arxiv.org/abs/1301.3614)
+
+[^8]: [Buys, Jan, and Phil Blunsom. "A Bayesian model for generative transition-based dependency parsing." arXiv preprint arXiv:1506.04334 (2015).](https://arxiv.org/abs/1506.04334)

examples/llm agent OR llm tool integration.md

@@ -0,0 +1,86 @@
+# A Systematic Review of Large Language Model Agent and Tool Integration
+
+This systematic review analyzes the current state of Large Language Model (LLM) agent and tool integration. LLMs are being integrated into various systems, but they lack access to external knowledge sources, limiting their usefulness in scientific applications. LLMs exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications. The review will discuss the historical background of this field, the motivation for this field and the problem it is trying to solve, and future developments in this field.
+
+## Table of contents
+
+1. Introduction: Large Language Models (LLMs) are being integrated into various systems. This section provides an overview of the field and the problem it is trying to solve.
+    1. Background: This subsection provides a brief history of LLMs and their development.
+    2. Motivation: This subsection discusses the motivation for integrating LLMs into various systems.
+    3. Problem Statement: This subsection defines the problem that LLM agent and tool integration is trying to solve.
+2. LLM Agent Integration: This section discusses the integration of LLMs into various systems as agents.
+    1. Application-Integrated LLMs: This subsection discusses the threat landscape of Application-Integrated LLMs and the new attack vectors they introduce.
+    2. Chemistry Tools: This subsection discusses the integration of chemistry tools with LLMs to augment their performance in chemistry-related problems.
+    3. Climate Resources: This subsection discusses the integration of climate resources with LLMs to overcome the limitations associated with imprecise language and deliver more reliable and accurate information in the critical domain of climate change.
+3. LLM Tool Integration: This section discusses the integration of LLMs into various systems as tools.
+    1. Labor Market Impact: This subsection investigates the potential implications of LLMs on the U.S. labor market and assesses occupations based on their alignment with LLM capabilities.
+    2. Medical Imaging: This subsection discusses the development of an image segmentation tool trained with the largest segmentation dataset and its extension on 3D Slicer.
+4. Conclusion: This section summarizes the findings of the systematic review and discusses future developments in the field.
+
+## Introduction: Large Language Models (LLMs) are being integrated into various systems. This section provides an overview of the field and the problem it is trying to solve.
+
+Large Language Models (LLMs) have recently shown strong performance in tasks across domains and are being adopted in practice and integrated into many systems, including integrated development environments (IDEs) and search engines [^1]. However, LLMs lack access to external knowledge sources, limiting their usefulness in scientific applications [^2]. LLMs exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications [^4]. The integration of LLMs into various systems as agents and tools is a growing field that aims to overcome these limitations and enhance the performance of LLMs in various domains. This systematic review analyzes the current state of LLM agent and tool integration, discusses the historical background of this field, the motivation for this field and the problem it is trying to solve, and future developments in this field.
+
+### Background: This subsection provides a brief history of LLMs and their development.
+
+Large Language Models (LLMs) have recently shown strong performance in various tasks across domains [^2]. LLMs are a type of artificial neural network that can process and generate natural language text. They have been developed over the past few decades, with early models such as the Hidden Markov Model and the n-gram model [^1]. However, the recent advancements in deep learning techniques have led to the development of more powerful LLMs, such as GPT-3 and T5 [^4]. These models have been trained on massive amounts of text data and can generate human-like text with high accuracy. LLMs have been integrated into various systems, including integrated development environments (IDEs), search engines, and content creation tools [^8][^1]. Despite their impressive capabilities, LLMs lack access to external knowledge sources, limiting their usefulness in scientific applications [^2]. The development of LLMs has significant economic, social, and policy implications, as they exhibit traits of general-purpose technologies [^4].
+
+### Motivation: This subsection discusses the motivation for integrating LLMs into various systems.
+
+Large Language Models (LLMs) have shown remarkable performance in various domains, including natural language processing, image recognition, and speech recognition. However, LLMs lack access to external knowledge sources, limiting their usefulness in scientific applications [^3]. To overcome this limitation, LLMs are being integrated into various systems, including chemistry tools [^2], climate resources [^3], and labor market impact analysis [^4]. The integration of LLMs into these systems aims to augment their performance and overcome the limitations associated with imprecise language, delivering more reliable and accurate information in critical domains such as climate change [^3]. Additionally, LLMs exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications [^4]. Therefore, the motivation for integrating LLMs into various systems is to enhance their performance and extend their applicability to scientific domains, while also exploring their potential economic, social, and policy implications.
+
+### Problem Statement: This subsection defines the problem that LLM agent and tool integration is trying to solve.
+
+Large Language Models (LLMs) are being integrated into various systems, but they lack access to external knowledge sources, limiting their usefulness in scientific applications [^3]. Moreover, LLMs exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications [^4]. The problem that LLM agent and tool integration is trying to solve is to enhance the performance of LLMs by integrating them with external knowledge sources and tools, enabling them to overcome their limitations and deliver more reliable and accurate information in various domains [^2][^3]. This systematic review aims to analyze the current state of LLM agent and tool integration and discuss future developments in this field.
+
+## LLM Agent Integration
+
+LLMs are being integrated into various systems as agents to perform complex tasks and make informed decisions. These agents can autonomously determine which actions to take, including utilizing various tools and observing their outputs or providing responses to user queries [^3]. By leveraging the LLM's vast knowledge and understanding of natural language, agents can efficiently navigate through an array of tools and select the most appropriate one based on the given context. This enables the LLM agent to provide reliable, accurate, and contextually relevant solutions in diverse applications and domains [^3]. 
+
+However, the integration of LLMs as agents also introduces new attack vectors. For instance, Application-Integrated LLMs might process poisoned content retrieved from the Web that contains malicious prompts pre-injected and selected by adversaries [^1]. This calls for an urgent evaluation of current mitigation techniques and an investigation of whether new techniques are needed to defend LLMs against these threats [^1]. 
+
+Moreover, LLM agents exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications [^3]. The versatility and adaptability of LLM agents make them an essential asset in various applications and domains, highlighting the immense potential for their future development and integration into increasingly complex and sophisticated AI systems [^3].
+
+### Application-Integrated LLMs
+
+LLMs are being integrated into various systems, including integrated development environments (IDEs) and search engines. However, LLMs lack access to external knowledge sources, limiting their usefulness in scientific applications [^1]. Recently, several ways to misalign LLMs using Prompt Injection (PI) attacks have been introduced. In such attacks, an adversary can prompt the LLM to produce malicious content or override the original instructions and the employed filtering schemes. These attacks assumed that the adversary is directly prompting the LLM. However, augmenting LLMs with retrieval and API calling capabilities (so-called Application-Integrated LLMs) induces a whole new set of attack vectors. These LLMs might process poisoned content retrieved from the Web that contains malicious prompts pre-injected and selected by adversaries. Adversaries can now attempt to indirectly inject the LLMs with prompts placed within publicly accessible sources, which might allow attackers to gain control of LLMs by crossing crucial security boundaries with a single search query. [^1]
+
+The resulting threat landscape of Application-Integrated LLMs needs to be systematically analyzed, and a variety of new attack vectors need to be discussed. The potential harm of these attacks calls for a more in-depth investigation of the generalizability of these attacks in practice. [^1]
+
+### Chemistry Tools
+
+LLMs have shown strong performance in tasks across domains, but they struggle with chemistry-related problems and lack access to external knowledge sources, limiting their usefulness in scientific applications [^2]. To overcome this limitation, ChemCrow, an LLM chemistry agent, has been introduced to accomplish tasks across organic synthesis, drug discovery, and materials design by integrating 13 expert-designed tools [^2]. ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. The evaluation, including both LLM and expert human assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks [^2]. The integration of expert-designed tools can help mitigate the hallucination issues commonly associated with these models, thus reducing the risk of inaccuracy [^2]. Employed responsibly, ChemCrow not only aids expert chemists and lowers barriers for non-experts but also fosters scientific advancement by bridging the gap between experimental and computational chemistry [^2].
+
+### Climate Resources
+
+LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, Kraus et al. [^3] make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. They demonstrate the effectiveness of their method through a prototype agent that retrieves emission data from ClimateWatch and leverages general Google search. By integrating these resources with LLMs, their approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance.
+
+## LLM Tool Integration: This section discusses the integration of LLMs into various systems as tools.
+
+LLMs are being integrated into various systems as tools to enhance their performance in specific domains. One such domain is medical imaging, where LLMs have been used to develop an image segmentation tool trained with the largest segmentation dataset and its extension on 3D Slicer [^7]. Another domain where LLMs are being integrated as tools is chemistry. ChemCrow is an implementation that integrates external tools through LangChain, as LLMs have been shown to perform better with tools [^2]. The implementation uses a limited set of tools, but it can be easily expanded depending on needs and availability. The tools used can be classified into general tools, molecular tools, and chemical reaction tools. The general tools include web search, which provides the language model with the ability to access relevant information from the web. The molecular tools include tools for molecular visualization and molecular property prediction, while the chemical reaction tools include tools for reaction prediction and retrosynthesis planning. 
+
+[^2]: Enhancing Large Language Models with Climate Resources
+[^7]: ART: Automatic multi-step reasoning and tool-use for large language models
+
+### Labor Market Impact
+
+LLMs, such as Generative Pre-trained Transformers (GPTs), have the potential to significantly affect a diverse range of occupations within the U.S. economy, demonstrating a key attribute of general-purpose technologies [^4]. This subsection investigates the potential implications of LLMs on the U.S. labor market and assesses occupations based on their alignment with LLM capabilities. Using a new rubric, around 80% of the U.S. workforce could have at least 10% of their work tasks affected by the introduction of LLMs, while approximately 19% of workers may see at least 50% of their tasks impacted [^4]. The projected effects span all wage levels, with higher-income jobs potentially facing greater exposure to LLM capabilities and LLM-powered software [^4]. Our analysis suggests that, with access to an LLM, about 15% of all worker tasks in the US could be completed significantly faster at the same level of quality. When incorporating software and tooling built on top of LLMs, this share increases to between 47 and 56% of all tasks [^4]. However, while the technical capacity for LLMs to make human labor more efficient appears evident, it is important to recognize that social, economic, regulatory, and other factors will influence actual labor productivity outcomes [^4]. The impact of LLMs on the economy will likely persist and increase, posing challenges for policymakers in predicting and regulating their trajectory [^4].
+
+### Medical Imaging: This subsection discusses the development of an image segmentation tool trained with the largest segmentation dataset and its extension on 3D Slicer.
+
+A new image segmentation tool called Segment Anything Model (SAM) has been developed and trained with the largest segmentation dataset at this time [^5]. SAM has demonstrated high-quality masks for image segmentation with good promptability and generalizability. However, the performance of the model on medical images requires further validation. To assist with the development, assessment, and utilization of SAM on medical images, an extension of SAM on 3D Slicer called Segment Any Medical Model (SAMM) has been introduced [^5]. SAMM achieves 0.6-second latency of a complete cycle and can infer image masks in nearly real-time. The integration of 3D Slicer with SAM enables researchers to conduct segmentation on medical images using the state-of-the-art LLM [^5]. This integration clears the path for validating SAM on medical images with 3D Slicer, an open-source software with abundant medical image analysis tools. By combining AI-based medical image models with the 3D Slicer software, SAMM provides a paradigmatic approach that enables users to directly enhance their research and work through the use of AI tools [^5].
+
+## Conclusion
+
+In conclusion, this systematic review has analyzed the current state of Large Language Model (LLM) agent and tool integration. LLMs are being integrated into various systems, but they lack access to external knowledge sources, limiting their usefulness in scientific applications [^2][^3]. LLMs exhibit traits of general-purpose technologies, indicating considerable economic, social, and policy implications [^4]. The review has discussed the historical background of this field, the motivation for this field and the problem it is trying to solve, and future developments in this field. The review has identified several areas where LLMs are being integrated as agents or tools, including chemistry tools [^2], climate resources [^3], and medical imaging [^5]. The review has also highlighted the potential threats associated with Application-Integrated LLMs, including novel prompt injection threats [^1]. Future developments in this field should focus on addressing these threats and improving the integration of LLMs into various systems to enhance their performance and usefulness in scientific applications.
+
+## References
+[^1]: [Greshake, Kai, et al. "More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models." arXiv preprint arXiv:2302.12173 (2023).](https://arxiv.org/abs/2302.12173)
+
+[^2]: [Bran, Andres M., et al. "ChemCrow: Augmenting large-language models with chemistry tools." arXiv preprint arXiv:2304.05376 (2023).](https://arxiv.org/abs/2304.05376)
+
+[^3]: [Kraus, Mathias, et al. "Enhancing Large Language Models with Climate Resources." arXiv preprint arXiv:2304.00116 (2023).](https://arxiv.org/abs/2304.00116)
+
+[^4]: [Eloundou, Tyna, et al. "Gpts are gpts: An early look at the labor market impact potential of large language models." arXiv preprint arXiv:2303.10130 (2023).](https://arxiv.org/abs/2303.10130)
+
+[^5]: [Liu, Yihao, et al. "Samm (segment any medical model): A 3d slicer integration to sam." arXiv preprint arXiv:2304.05622 (2023).](https://arxiv.org/abs/2304.05622)