{"id":5142,"date":"2023-01-22T20:55:42","date_gmt":"2023-01-22T20:55:42","guid":{"rendered":"https:\/\/www.dinu.at\/profile\/home\/?p=5142"},"modified":"2023-01-22T20:57:19","modified_gmt":"2023-01-22T20:57:19","slug":"a-neuro-symbolic-perspective-on-large-language-models-llms","status":"publish","type":"post","link":"https:\/\/www.dinu.at\/profile\/home\/a-neuro-symbolic-perspective-on-large-language-models-llms\/","title":{"rendered":"A Neuro-Symbolic Perspective on Large Language Models (LLMs)"},"content":{"rendered":"\n
\"\"<\/a><\/figure>\n\n\n
\n\n <\/div>\n\n\n\n
\"\"<\/a><\/figure>\n\n\n\n

<\/p>\n\n\n\n

We are excited to present our work, combining the power of a symbolic approach and Large Language Models (LLMs). Our Symbolic API bridges the gap between classical programming (Software 1.0) and differentiable programming (Software 2.0). Conceptually, our framework uses neural networks - specifically LLMs - at its core, and composes operations based on task-specific zero-shot or few-shot prompting. We adopt a divide and conquer approach to decompose a complex problem into smaller problems. Therefore, each operation solves a simple task. By re-combining these operations, we can solve the complex problem. Furthermore, we demonstrate how to combine the strengths of both neural networks and symbolic reasoning to create AI systems that can solve a wide range of hard tasks. This includes fact-based generation of text, flow control of a generative process towards a desired outcome, and interpretability within generative processes.<\/p>\n","protected":false},"excerpt":{"rendered":"

We are excited to present our work, combining the power of a symbolic approach and Large Language Models (LLMs). Our Symbolic API bridges the gap between classical programming (Software 1.0) and differentiable programming (Software 2.0). Conceptually, our framework uses neural networks – specifically LLMs – at its core, and composes operations based on task-specific zero-shot […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true},"categories":[1],"tags":[],"jetpack_featured_media_url":"","jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p7SrVj-1kW","jetpack-related-posts":[{"id":4721,"url":"https:\/\/www.dinu.at\/profile\/home\/lighter-dependency-injection-with-pytorch\/","url_meta":{"origin":5142,"position":0},"title":"Lighter: Dependency Injection for PyTorch","date":"9. June 2021","format":false,"excerpt":"Python & Machine Learning: If you ever thought that handling all those kwargs, dictionaries of config properties, or huge method parameter listings feels tedious and somewhat like a step back in the evolution of programming language, well... then this is because you are completely right! It is a step back.\u2026","rel":"","context":"In "General"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":4493,"url":"https:\/\/www.dinu.at\/profile\/home\/bachelor-thesis\/","url_meta":{"origin":5142,"position":1},"title":"Bachelor Thesis","date":"21. July 2015","format":false,"excerpt":"Cross-Language integration for the Common Language Runtime of the .NET Framework Institute: University of Applied Sciences Upper-Austria Field of Study: Software Engineering Author: Dinu Marius-ConstantinPrelude The basic idea is to translate any programming language\u00a0code into .NET Intermediate Language (IL) code by using the open source .NET Compiler Platform (Roslyn). Roslyn\u2026","rel":"","context":"In "Education"","img":{"alt_text":"","src":"https:\/\/i1.wp.com\/www.dinu.at\/wp-content\/uploads\/2015\/07\/keep-calm-and-write-bachelor-thesis-1.png?fit=600%2C700&ssl=1&resize=350%2C200","width":350,"height":200},"classes":[]},{"id":5080,"url":"https:\/\/www.dinu.at\/profile\/home\/ensemble-learning-for-domain-adaptation-by-importance-weighted-least-squares\/","url_meta":{"origin":5142,"position":2},"title":"Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation","date":"13. August 2022","format":false,"excerpt":"Abstract We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a\u2026","rel":"","context":"In "General"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":4697,"url":"https:\/\/www.dinu.at\/profile\/home\/align-rudder-learning-from-few-demonstrations-by-reward-redistribution\/","url_meta":{"origin":5142,"position":3},"title":"Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution","date":"30. September 2020","format":false,"excerpt":"Reinforcement Learning algorithms require a large number of samples to solve complex tasks with sparse and delayed rewards. Complex tasks can often be hierarchically decomposed into sub-tasks. A step in the Q-function can be associated with solving a sub-task, where the expectation of the return increases. RUDDER has been introduced\u2026","rel":"","context":"In "General"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":5059,"url":"https:\/\/www.dinu.at\/profile\/home\/xai-and-strategy-extraction-via-reward-redistribution\/","url_meta":{"origin":5142,"position":4},"title":"XAI and Strategy Extraction via Reward Redistribution","date":"17. October 2020","format":false,"excerpt":"Abstract In reinforcement learning, an agent interacts with an environment from which it receives rewards, that are then used to learn a task. However, it is often unclear what strategies or concepts the agent has learned to solve the task. Thus, interpretability of the agent\u2019s behavior is an important aspect\u2026","rel":"","context":"In "General"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":4538,"url":"https:\/\/www.dinu.at\/profile\/home\/operation-phrike\/","url_meta":{"origin":5142,"position":5},"title":"Operation Phrike","date":"7. September 2016","format":false,"excerpt":"Operation Phrike has been created by students from the University of Applied Sciences Upper-Austria (Bachelor Software Engineering). It is basically a simulation software for military virtual reality combat scenarios. To create an authentic battlefield experience we use the Oculus Rift in combination with the Unreal Gameing-Engine. During the simulation process\u2026","rel":"","context":"In "Education"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"builder_content":"","_links":{"self":[{"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/posts\/5142"}],"collection":[{"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/comments?post=5142"}],"version-history":[{"count":4,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/posts\/5142\/revisions"}],"predecessor-version":[{"id":5149,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/posts\/5142\/revisions\/5149"}],"wp:attachment":[{"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/media?parent=5142"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/categories?post=5142"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dinu.at\/profile\/home\/wp-json\/wp\/v2\/tags?post=5142"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}