Critique ability, i.e., the capability of Large Language Models (LLMs) to identify

Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of each fact using a multi-step reasoning process comprising sending search queries to Google Search and determining whether a fact is supported by the search results. Furthermore, we propose extending F1 score as an aggregated metric for long-form factuality. To do so, we balance the percentage of supported facts in a response (precision) with the percentage of provided facts relative to a hyperparameter representing a user's preferred response length (recall).Empirically, we demonstrate that LLM agents can outperform crowdsourced human annotators--on a set of 16k individual facts, SAFE agrees with crowdsourced human annotators 72% of the time, and on a random subset of 100 disagreement cases, SAFE wins 76% of the time. At the same time, SAFE is more than 20 times cheaper than human annotators. We also benchmark thirteen language models on LongFact across four model families (Gemini, GPT, Claude, and PaLM-2), finding that larger language models generally achieve better long-form factuality.

Understanding different human attributes and how they affect model behavior may become a standard need for all model creation and usage, from traditional computer vision tasks to the newest multimodal generative AI systems. In computer vision specifically, we have relied on datasets augmented with perceived attribute signals (eg, gender presentation, skin tone, and age) and benchmarks enabled by these datasets. Typically labels for these tasks come from human annotators. However, annotating attribute signals, especially skin tone, is a difficult and subjective task. Perceived skin tone is affected by technical factors, like lighting conditions, and social factors that shape an annotator's lived experience.This paper examines the subjectivity of skin tone annotation through a series of annotation experiments using the Monk Skin Tone (MST) scale~\cite{Monk2022Monk}, a small pool of professional photographers, and a much larger pool of trained crowdsourced annotators. Along with this study we release the Monk Skin Tone Examples (MST-E) dataset, containing 1515 images and 31 videos spread across the full MST scale. MST-E is designed to help train human annotators to annotate MST effectively.Our study shows that annotators can reliably annotate skin tone in a way that aligns with an expert in the MST scale, even under challenging environmental conditions. We also find evidence that annotators from different geographic regions rely on different mental models of MST categories resulting in annotations that systematically vary across regions. Given this, we advise practitioners to use a diverse set of annotators and a higher replication count for each image when annotating skin tone for fairness research.