Related papers: Kani: A Lightweight and Highly Hackable Framework …
Effective scaling and a flexible task interface enable large language models to excel at many tasks. We present PaLI (Pathways Language and Image model), a model that extends this approach to the joint modeling of language and vision. PaLI…
Large language models (LLMs), due to their advanced natural language capabilities, have seen significant success in applications where the user interface is usually a conversational artificial intelligence (AI) agent and engages the user…
The success of large language models has shifted the evaluation paradigms in natural language processing (NLP). The community's interest has drifted towards comparing NLP models across many tasks, domains, and datasets, often at an extreme…
While the increased integration of AI technologies into interactive systems enables them to solve an increasing number of tasks, the black-box problem of AI models continues to spread throughout the interactive system as a whole.…
Asynchronous Many-Task Systems (AMTs) exhibit different communication patterns from traditional High-Performance Computing (HPC) applications, characterized by asynchrony, concurrency, and multithreading. Existing communication libraries…
This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…
Large Language Models (LLMs) have demonstrated remarkable language understanding and generation capabilities. However, training, deploying, and accessing these models pose notable challenges, including resource-intensive demands, extended…
Large-scale language models (LLMs), such as ChatGPT, are becoming increasingly sophisticated and exhibit human-like capabilities, playing an essential role in assisting humans in a variety of everyday tasks. An important application of AI…
Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off:…
This work presents an analytical framework for the design and analysis of LLM-based algorithms, i.e., algorithms that contain one or multiple calls of large language models (LLMs) as sub-routines and critically rely on the capabilities of…
The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…
In software engineering, a great number of new approaches are being actively researched, and a lot of tools are being developed based on them. These tools require a framework for their creation and an opportunity to be used by potential…
The licas (lightweight Internet-based communication for autonomic services) system is a Java-based open source framework for building service-based networks, similar to what you would use a Cloud or SOA platform for. The framework comes…
Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation…
At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely…
For complex data types such as multimedia, traditional data management methods are not suitable. Instead of attribute matching approaches, access methods based on object similarity are becoming popular. Recently, this resulted in an…
Traditional language models have been extensively evaluated for software engineering domain, however the potential of ChatGPT and Gemini have not been fully explored. To fulfill this gap, the paper in hand presents a comprehensive case…
This paper presents an overview of Carnap, a free and open framework for the development of formal reasoning applications. Carnap's design emphasizes flexibility, extensibility, and rapid prototyping. Carnap-based applications are written…
Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the Language-Models-as-a-Service (LMaaS) paradigm. In contrast with…
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be…