Agency, the capacity to proactively shape events, is crucial to how humans interact and collaborate with other humans. In this paper, we investigate Agency as a potentially desirable function of dialogue agents, and how it can be measured and controlled. We build upon the social-cognitive theory of Bandura (2001) to develop a framework of features through which Agency is expressed in dialogue -- indicating what you intend to do (Intentionality), motivating your intentions (Motivation), having self-belief in intentions (Self-Efficacy), and being able to self-adjust (Self-Regulation). We collect and release a new dataset of 83 human-human collaborative interior design conversations containing 908 conversational snippets annotated for Agency features. Using this dataset, we explore methods for measuring and controlling Agency in dialogue systems. Automatic and human evaluation show that although a baseline GPT-3 model can express Intentionality, models that explicitly manifest features associated with high Motivation, Self-Efficacy, and Self-Regulation are better perceived as being highly agentive. This work has implications for the development of dialogue systems with varying degrees of Agency in collaborative tasks.

Large language models (LLMs) have demonstrated impressive few-shot learning capabilities, but they often underperform compared to fine-tuned models on challenging tasks. Furthermore, their large size and restricted access only through APIs make task-specific fine-tuning impractical. Moreover, LLMs are sensitive to different aspects of prompts (e.g., the selection and order of demonstrations) and can thus require time-consuming prompt engineering. In this light, we propose a method to correct LLM outputs without relying on their weights. First, we generate a pool of candidates by few-shot prompting an LLM. Second, we refine the LLM-generated outputs using a smaller model, the LM-corrector (LMCor), which is trained to rank, combine and rewrite the candidates to produce the final target output. Our experiments demonstrate that even a small LMCor model (250M) substantially improves the few-shot performance of LLMs (62B) across diverse tasks. Moreover, we illustrate that the LMCor exhibits robustness against different prompts, thereby minimizing the need for extensive prompt engineering. Finally, we showcase that the LMCor can be seamlessly integrated with different LLMs at inference time, serving as a plug-and-play module to improve their performance.

Australian philosopher Peter Singer's book Animal Liberation, published in 1975, exposed the realities of life for animals in factory farms and testing laboratories and provided a powerful moral basis for rethinking our relationship to them. Now, nearly 50 years on, Singer, 76, has a revised version titled Animal Liberation Now. It comes on the heels of an updated edition of his popular Ethics in the Real World, a collection of short essays dissecting important current events, first published in 2016. Singer, a utilitarian, is a professor of bioethics at Princeton University. In addition to his work on animal ethics, he is also regarded as the philosophical originator of a philanthropic social movement known as effective altruism, which argues for weighing up causes to achieve the most good.

We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: we build an anti-LM based on previously generated text and use this anti-LM to penalize future generation of what has been generated. The anti-LM can be implemented as simple as an n-gram language model or a vectorized variant. In this way, FSD introduces no extra model parameters and negligible computational overhead (FSD can be as fast as greedy search). Despite the simplicity, FSD is surprisingly effective; Experiments show that FSD can outperform the canonical methods to date (i.e., nucleus sampling) as well as several strong baselines that were proposed recently.

Large Language Models (LLMs) can generate texts that carry the risk of various misuses, including plagiarism, planting fake reviews on e-commerce platforms, or creating fake social media postings that can sway election results. Detecting whether a text is machine-generated has thus become increasingly important. While machine-learning-based detection strategies exhibit superior performance, they often lack generalizability, limiting their practicality. In this work, we introduce GPT Paternity Test (GPT-Pat), which reliably detects machine-generated text across varied datasets. Given a text under scrutiny, we leverage ChatGPT to generate a corresponding question and provide a re-answer to the question. By comparing the similarity between the original text and the generated re-answered text, it can be determined whether the text is machine-generated. GPT-Pat consists of a Siamese network to compute the similarity between the original text and the generated re-answered text and a binary classifier. Our method achieved an average accuracy of 94.57% on four generalization test sets, surpassing the state-of-the-art RoBERTa-based method by 12.34%. The accuracy drop of our method is only about half of that of the RoBERTa-based method when it is attacked by re-translation and polishing.

Generative AI tools introduce new and accessible forms of media creation for youth. They also raise ethical concerns about the generation of fake media, data protection, privacy and ownership of AI-generated art. Since generative AI is already being used in products used by youth, it is critical that they understand how these tools work and how they can be used or misused. In this work, we facilitated students' generative AI learning through expression of their imagined future identities. We designed a learning workshop - Dreaming with AI - where students learned about the inner workings of generative AI tools, used text-to-image generation algorithms to create their imaged future dreams, reflected on the potential benefits and harms of generative AI tools and voiced their opinions about policies for the use of these tools in classrooms. In this paper, we present the learning activities and experiences of 34 high school students who engaged in our workshops. Students reached creative learning objectives by using prompt engineering to create their future dreams, gained technical knowledge by learning the abilities, limitations, text-visual mappings and applications of generative AI, and identified most potential societal benefits and harms of generative AI.

We've collected some of the articles, opinion pieces, videos and resources relating to large language models (LLMs). Some of these links also cover other generative models. We will periodically update this list to add any further resources of interest. This article represents the first update.

Over the past few weeks, there's been some very public hand-wringing about artificial intelligence--a lot of it coming from people who have made A.I. their life's work. Geoffrey Hinton, dubbed the "godfather of A.I.," recently left his job at Google to embark upon a sort of media tour warning about the dangers of the technology. There was a public letter from Elon Musk and others calling for a pause in A.I. development and an essay in Time from theorist Eliezer Yudkowsky saying generative A.I. can harm humanity--or even end it. On Friday's episode of What Next: TBD, I spoke with Meredith Whittaker, president of the Signal Foundation and co-founder of the AI Now Institute at NYU, to sort through the real threat of A.I. and what the doomerism discourse is missing. Our conversation has been edited and condensed for clarity. What do you make of the concerns raised by Geoffrey Hinton and others when it comes to A.I. safety?

Open-Domain Question Answering (ODQA) aims at answering factoid questions without explicitly providing specific background documents. In a zero-shot setting, this task is more challenging since no data is available to train customized models like Retriever-Readers. Recently, Large Language Models (LLMs) like GPT-3 have shown their power in zero-shot ODQA with direct prompting methods, but these methods are still far from releasing the full powerfulness of LLMs only in an implicitly invoking way. In this paper, we propose a Self-Prompting framework to explicitly utilize the massive knowledge stored in the parameters of LLMs and their strong instruction understanding abilities. Concretely, we prompt LLMs step by step to generate multiple pseudo QA pairs with background passages and explanations from scratch and then use those generated elements for in-context learning. Experimental results show our method surpasses previous SOTA methods significantly on three widely-used ODQA datasets, and even achieves comparable performance with some Retriever-Reader models fine-tuned on full training data.

Thank you for joining us on "The cloud hub: From cloud chaos to clarity." Watch Bonnie Holub, Infosys AI evangelist, speak with Caroline Coward, information science manager and library group supervisor at NASA Jet Propulsion Laboratory, about infusing an ethical foundation in AI algorithm development.