As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presence or absence of a broad set of high-level abstract concepts within the embeddings computed in an LLM - which is what we might say a model is "thinking" about. Such probes should be low-cost and easily applicable to any LLM, so that monitoring for many concepts is possible during normal operation.In this paper, we take the first steps towards developing the capability of creating many such probes by defining and executing examples of the key tasks needed: first, the careful delineation of a high-level abstract concept through the creation of a dataset with the concept both present and then absent. Then, the training and testing of a set of linear probes to detect the concept on any layer of an LLM, including an exploration of the complexity of the probe needed. Finally, we show that such probes can track concepts across larger contexts. This is done with four separate concepts and three different LLMs. When this process is scaled to many more concepts, it will create the ability to monitor new models.

While large language models (LLMs) afford new possibilities for user modeling and approximation of human behaviors, they often fail to capture the multidimensional nuances of individual users. In this work, we introduce PersonaTwin, a multi-tier prompt conditioning framework that builds adaptive digital twins by integrating demographic, behavioral, and psychometric data. Using a comprehensive data set in the healthcare context of more than 8,500 individuals, we systematically benchmark PersonaTwin against standard LLM outputs, and our rigorous evaluation unites state-of-the-art text similarity metrics with dedicated demographic parity assessments, ensuring that generated responses remain accurate and unbiased. Experimental results show that our framework produces simulation fidelity on par with oracle settings. Moreover, downstream models trained on persona-twins approximate models trained on individuals in terms of prediction and fairness metrics across both GPT-4o-based and Llama-based models. Together, these findings underscore the potential for LLM digital twin-based approaches in producing realistic and emotionally nuanced user simulations, offering a powerful tool for personalized digital user modeling and behavior analysis.

Large language models (LLMs) are increasingly applied to finance, yet challenges remain in aligning their capabilities with real-world institutional demands. In this survey, we provide a systematic, dual-perspective review bridging financial practice and LLM research. From a practitioner-centric standpoint, we introduce a functional taxonomy covering five core financial domains—Data Analysis, Investment Research, Trading, Investment Management, and Risk Management—mapping each to representative tasks, datasets, and institutional constraints. From a research-focused perspective, we analyze key modeling challenges, including numerical reasoning limitations, prompt sensitivity, and lack of real-time adaptability. We comprehensively catalog over 30 financial benchmarks and 20 representative models, and compare them across modalities, tasks, and deployment limitations. Finally, we identify open challenges and outline emerging directions such as continual adaptation, coordination-aware multi-agent systems, and privacy-compliant deployment. We emphasize deeper researcher–practitioner collaboration and transparent model architectures as critical pathways to safer and more scalable AI adoption in finance.

The conversational capabilities of Large Language Models (LLMs) suggest that they may be able to perform as automated talk therapists. It is crucial to know if these systems would be effective and adhere to known standards. We present a counsellor chatbot that focuses on motivating tobacco smokers to quit smoking. It uses a state-of-the-art LLM and a widely applied therapeutic approach called Motivational Interviewing (MI), and was evolved in collaboration with clinician-scientists with expertise in MI. We also describe and validate an automated assessment of both the chatbot’s adherence to MI and client responses. The chatbot was tested on 106 participants, and their confidence that they could succeed in quitting smoking was measured before the conversation and one week later. Participants’ confidence increased by an average of 1.7 on a 0-10 scale. The automated assessment of the chatbot showed adherence to MI standards in 98% of utterances, higher than human counsellors. The chatbot scored well on a participant-reported metric of perceived empathy but lower than typical human counsellors. Furthermore, participants’ language indicated a good level of motivation to change, a key goal in MI. These results suggest that the automation of talk therapy with a modern LLM has promise.

Using data from Nintemann et al. (2020), we explore the variability in complexity and informativity across spatial demonstrative systems using spatial deictic lexicons from 223 languages. We argue from an information-theoretic perspective (Shannon, 1948) that spatial deictic lexicons are efficient in communication, balancing informativity and complexity. Specifically, we find that under an appropriate choice of cost function and need probability over meanings, among all the 21146 theoretically possible spatial deictic lexicons, those adopted by real languages lie near an efficient frontier. Moreover, we find that the conditions that the need probability and the cost function need to satisfy are consistent with the cognitive science literature regarding the source-goal asymmetry. We also show that the data are better explained by introducing a notion of systematicity, which is not currently accounted for in Information Bottleneck approaches to linguistic efficiency.