Related papers: Debate Helps Weak-to-Strong Generalization
Deep learning has largely improved the performance of various natural language processing (NLP) tasks. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this chapter, we will introduce our…
Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such…
Large language models are usually fine-tuned to align with human preferences. However, fine-tuning a large language model can be challenging. In this work, we introduce $\textit{weak-to-strong search}$, framing the alignment of a large…
In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…
We introduce Integrated Weak Learning, a principled framework that integrates weak supervision into the training process of machine learning models. Our approach jointly trains the end-model and a label model that aggregates multiple…
Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibration by capturing uncertainty, prior studies conflate these benefits with the implicit…
In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM's performance exceeds humans and surpasses the…
A rising vision for AI in the open world centers on the development of systems that can complement humans for perceptual, diagnostic, and reasoning tasks. To date, systems aimed at complementing the skills of people have employed models…
Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…
Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge. In this work, we consider few-shot classification, and aim to shed light on what makes some novel classes easier…
Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…
As machine learning models continue to increase in complexity, collecting large hand-labeled training sets has become one of the biggest roadblocks in practice. Instead, weaker forms of supervision that provide noisier but cheaper labels…
Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated…
Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…
We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…
Multi-persona debate systems powered by large language models (LLMs) show promise in reducing confirmation bias, which can fuel echo chambers and social polarization. However, empirical evidence remains limited on whether they meaningfully…
Warning: This research studies AI persuasion and bias amplification that could be misused; all experiments are for safety evaluation. Large Language Models (LLMs) now generate convincing, human-like text and are widely used in content…
The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated…
Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch from their old paradigms to machine learning. Interestingly,…
As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term…