Reinforcement Learning (RL) finetuning is an important step in training language models (LMs) to behave in specific ways and follow human etiquette. In today’s applications, RL finetuning involves multiple goals due to various human preferences and uses. The multi-objective finetuning (MOFT) is needed to train a multi-objective LM to overcome the limitations of single-objective finetuning…
Parameter-efficient fine-tuning (PEFT) methods have become essential in machine learning. They allow large models to adapt to new tasks without extensive computational resources. By fine-tuning only a small subset of parameters while keeping most of the model frozen, PEFT methods aim to make the adaptation process more efficient and accessible. This approach is crucial for…
Recent advancements in LLM capabilities have increased their usability by enabling them to do a broader range of general activities autonomously. The existing methods for expressing and running LM programs could be more efficient, although they are widely used. There are two main obstacles to effective LM program utilization: The non-deterministic character of LLMs makes…
Causal effect estimation is crucial for understanding the impact of interventions in various domains, such as healthcare, social sciences, and economics. This area of research focuses on determining how changes in one variable cause changes in another, which is essential for informed decision-making. Traditional methods often involve extensive data collection and structured experiments, which can…
Competition significantly shapes human societies, influencing economics, social structures, and technology. Traditional research on competition, relying on empirical studies, is limited by data accessibility and lacks micro-level insights. Agent-based modeling (ABM) emerged to overcome these limitations, progressing from rule-based to machine learning-based agents. However, these approaches still struggle to accurately simulate complex human behavior. The…
Evaluating model performance is essential in the significantly advancing fields of Artificial Intelligence and Machine Learning, especially with the introduction of Large Language Models (LLMs). This review procedure helps understand these models’ capabilities and create dependable systems based on them. However, what is referred to as Questionable Research Practices (QRPs) frequently jeopardize the integrity of…
Autonomous web navigation focuses on developing AI agents capable of performing complex online tasks. These tasks range from data retrieval and form submissions to more intricate activities like finding the cheapest flights or booking accommodations. By leveraging large language models (LLMs) and other AI methodologies, autonomous web navigation aims to enhance productivity in both consumer…
Generative Artificial Intelligence (GenAI), particularly large language models (LLMs) like ChatGPT, has revolutionized the field of natural language processing (NLP). These models can produce coherent and contextually relevant text, enhancing applications in customer service, virtual assistance, and content creation. Their ability to generate human-like text stems from training on vast datasets and leveraging deep learning…
Aligning models with human preferences poses significant challenges in AI research, particularly in high-dimensional and sequential decision-making tasks. Traditional Reinforcement Learning from Human Feedback (RLHF) methods require learning a reward function from human feedback and then optimizing this reward using RL algorithms. This two-phase approach is computationally complex, often leading to high variance in policy…
The landscape of artificial intelligence has seen significant advancements with the introduction of state-of-the-art language models. Among the leading models are Llama 3.1, GPT-4o, and Claude 3.5. Each model brings unique capabilities and improvements, reflecting the ongoing evolution of AI technology. Let’s analyze these three prominent models, examining their strengths, architectures, and use cases. Llama…