A long-standing ambition for artificial intelligence (AI) in biomedicine is the development of AI systems that could eventually make major scientific discoveries, with the potential to be worthy of a Nobel Prize--fulfilling the Nobel Turing Challenge [1]. While the concept of an "AI scientist" is aspirational, advances in agent-based AI pave the way to the development of AI agents as conversable systems capable of skeptical learning and reasoning that coordinate large language models (LLMs), machine learning (ML) tools, experimental platforms, or even combinations of them [2-5] (Figure 1). The complexity of biological problems requires a multistage approach, where decomposing complex questions into simpler tasks is necessary. AI agents can break down a problem into manageable subtasks, which can then be addressed by agents with specialized functions for targeted problem-solving and integration of scientific knowledge, paving the way toward a future in which a major biomedical discovery is made solely by AI [2, 6].

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. LongFact, SAFE, and all experimental code are available at https://github.com/google-deepmind/long-form-factuality.

Welcome to our monthly digest, where you can catch up with any AIhub stories you may have missed, peruse the latest news, recap recent events, and more. This month, we find out about explainability and human-robot interaction, serverless computing for machine learning, and deep reinforcement learning for communication networks. We also chat to AAAI President Francesca Rossi, and congratulate the ACM/SIGAI Autonomous Agents Research Award winner Catholijn Jonker. "AI used to be a scientific and technical field, now it has become a socio-technical discipline." AIhub ambassador Andrea Rafai caught up with AAAI President Francesca Rossi to ask about her research, regulation of AI, and the UN sustainable development goals: Interview with Francesca Rossi – talking sustainable development goals, AI regulation, and AI ethics.

Recent advancements in Large Language Models (LLMs) have significantly increased their presence in human-facing Artificial Intelligence (AI) applications. However, LLMs could reproduce and even exacerbate stereotypical outputs from training data. This work introduces the Multi-Grain Stereotype (MGS) dataset, encompassing 51,867 instances across gender, race, profession, religion, and stereotypical text, collected by fusing multiple previously publicly available stereotype detection datasets. We explore different machine learning approaches aimed at establishing baselines for stereotype detection, and fine-tune several language models of various architectures and model sizes, presenting in this work a series of stereotypes classifier models for English text trained on MGS. To understand whether our stereotype detectors capture relevant features (aligning with human common sense) we utilise a variety of explanainable AI tools, including SHAP, LIME, and BertViz, and analyse a series of example cases discussing the results. Finally, we develop a series of stereotype elicitation prompts and evaluate the presence of stereotypes in text generation tasks with popular LLMs, using one of our best performing previously presented stereotypes detectors. Our experiments yielded several key findings: i) Training stereotype detectors in a multi-dimension setting yields better results than training multiple single-dimension classifiers.ii) The integrated MGS Dataset enhances both the in-dataset and cross-dataset generalisation ability of stereotype detectors compared to using the datasets separately.

Media outlets are becoming more partisan and polarized nowadays. In this paper, we identify media bias at the sentence level, and pinpoint bias sentences that intend to sway readers' opinions. As bias sentences are often expressed in a neutral and factual way, considering broader context outside a sentence can help reveal the bias. In particular, we observe that events in a bias sentence need to be understood in associations with other events in the document. Therefore, we propose to construct an event relation graph to explicitly reason about event-event relations for sentence-level bias identification. The designed event relation graph consists of events as nodes and four common types of event relations: coreference, temporal, causal, and subevent relations. Then, we incorporate event relation graph for bias sentences identification in two steps: an event-aware language model is built to inject the events and event relations knowledge into the basic language model via soft labels; further, a relation-aware graph attention network is designed to update sentence embedding with events and event relations information based on hard labels. Experiments on two benchmark datasets demonstrate that our approach with the aid of event relation graph improves both precision and recall of bias sentence identification.

Retired Navy Adm. William McRaven's nearly 40-year career in the U.S. military has spanned everything from deployments as a Navy SEAL, hunting down high-value targets overseas, commanding U.S Special Operations forces in Iraq and Afghanistan, and advising Presidents George W. Bush and Barack Obama. But McRaven is best known for planning and overseeing the 2011 raid that ended with the death of Osama bin Laden. In December that year, McRaven was named as a runner-up for TIME's Person of the Year for his role in the operation. "There is nobody in the U.S. government that thinks we can kill our way to victory, certainly not the special-operations guys," he told TIME in 2011, "but what happens is, by capturing and killing some of these high-value targets, we buy space and time for the rest of the government to work." After retiring from the U.S. military in 2014, McRaven served as the chancellor of the University of Texas System and has written several books on leadership.

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection of LLM-generated text from its human-written counterpart. In this paper, we introduce a general and flexible framework for reasoning about the statistical efficiency of watermarks and designing powerful detection rules. Inspired by the hypothesis testing formulation of watermark detection, our framework starts by selecting a pivotal statistic of the text and a secret key -- provided by the LLM to the verifier -- to enable controlling the false positive rate (the error of mistakenly detecting human-written text as LLM-generated). Next, this framework allows one to evaluate the power of watermark detection rules by obtaining a closed-form expression of the asymptotic false negative rate (the error of incorrectly classifying LLM-generated text as human-written). Our framework further reduces the problem of determining the optimal detection rule to solving a minimax optimization program. We apply this framework to two representative watermarks -- one of which has been internally implemented at OpenAI -- and obtain several findings that can be instrumental in guiding the practice of implementing watermarks. In particular, we derive optimal detection rules for these watermarks under our framework. These theoretically derived detection rules are demonstrated to be competitive and sometimes enjoy a higher power than existing detection approaches through numerical experiments.

MindScape aims to study the benefits of integrating time series behavioral patterns (e.g., conversational engagement, sleep, location) with Large Language Models (LLMs) to create a new form of contextual AI journaling, promoting self-reflection and well-being. We argue that integrating behavioral sensing in LLMs will likely lead to a new frontier in AI. In this Late-Breaking Work paper, we discuss the MindScape contextual journal App design that uses LLMs and behavioral sensing to generate contextual and personalized journaling prompts crafted to encourage self-reflection and emotional development. We also discuss the MindScape study of college students based on a preliminary user study and our upcoming study to assess the effectiveness of contextual AI journaling in promoting better well-being on college campuses. MindScape represents a new application class that embeds behavioral intelligence in AI.

Officially, the appointment started in January and lasts three months. But Reben's relationship with the San Francisco–based AI firm seems casual: "It's a little fuzzy, because I'm the first, and we're figuring stuff out. I'm probably going to keep working with them." In fact, Reben has been working with OpenAI for years already. Five years ago, he was invited to try out an early version of GPT-3 before it was released to the public. "I got to play around with that quite a bit and made a few artworks," he says.

When prompting language models to complete a task, users often leave important aspects unsaid. While asking questions could resolve this ambiguity (GATE; Li et al., 2023), models often struggle to ask good questions. We explore a language model's ability to self-improve (STaR; Zelikman et al., 2022) by rewarding the model for generating useful questions-a simple method we dub STaR-GATE. We generate a synthetic dataset of 25,500 unique persona-task prompts to simulate conversations between a pretrained language model-the Questioner-and a Roleplayer whose preferences are unknown to the Questioner. By asking questions, the Questioner elicits preferences from the Roleplayer. The Questioner is iteratively finetuned on questions that increase the probability of high-quality responses to the task, which are generated by an Oracle with access to the Roleplayer's latent preferences. After two iterations of self-improvement, the Questioner asks better questions, allowing it to generate responses that are preferred over responses from the initial model on 72% of tasks. Our results indicate that teaching a language model to ask better questions leads to better personalized responses.