Thomas Haigh (thomas.haigh@gmail.com) is a professor of history at the University of Wisconsin--Milwaukee, WI, USA, and a Comenius visiting professor at Siegen University, Germany.

The great behavioral heterogeneity observed between individuals with the same psychiatric disorder and even within one individual over time complicates both clinical practice and biomedical research. However, modern technologies are an exciting opportunity to improve behavioral characterization. Existing psychiatry methods that are qualitative or unscalable, such as patient surveys or clinical interviews, can now be collected at a greater capacity and analyzed to produce new quantitative measures. Furthermore, recent capabilities for continuous collection of passive sensor streams, such as phone GPS or smartwatch accelerometer, open avenues of novel questioning that were previously entirely unrealistic. Their temporally dense nature enables a cohesive study of real-time neural and behavioral signals. To develop comprehensive neurobiological models of psychiatric disease, it will be critical to first develop strong methods for behavioral quantification. There is huge potential in what can theoretically be captured by current technologies, but this in itself presents a large computational challenge -- one that will necessitate new data processing tools, new machine learning techniques, and ultimately a shift in how interdisciplinary work is conducted. In my thesis, I detail research projects that take different perspectives on digital psychiatry, subsequently tying ideas together with a concluding discussion on the future of the field. I also provide software infrastructure where relevant, with extensive documentation. Major contributions include scientific arguments and proof of concept results for daily free-form audio journals as an underappreciated psychiatry research datatype, as well as novel stability theorems and pilot empirical success for a proposed multi-area recurrent neural network architecture.

Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. We also demonstrate that our approach improves the factual validity of generated content, reducing fallacious answers and hallucinations that contemporary models are prone to. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we investigate. Overall, our findings suggest that such "society of minds" approach has the potential to significantly advance the capabilities of LLMs and pave the way for further breakthroughs in language generation and understanding.

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by truth-seeking mechanisms in law, we propose a factuality evaluation framework for LMs that is based on cross-examination. Our key idea is that an incorrect claim is likely to result in inconsistency with other claims that the model generates. To discover such inconsistencies, we facilitate a multi-turn interaction between the LM that generated the claim and another LM (acting as an examiner) which introduces questions to discover inconsistencies. We empirically evaluate our method on factual claims made by multiple recent LMs on four benchmarks, finding that it outperforms existing methods and baselines, often by a large gap. Our results demonstrate the potential of using interacting LMs for capturing factual errors.

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.