As large language models (LLMs) grow increasingly adept at processing unstructured text data, they offer new opportunities to enhance data curation workflows. This paper explores the evolution of LLM adoption among practitioners at a large technology company, evaluating the impact of LLMs in data curation tasks through participants' perceptions, integration strategies, and reported usage scenarios. Through a series of surveys, interviews, and user studies, we provide a timely snapshot of how organizations are navigating a pivotal moment in LLM evolution. In Q2 2023, we conducted a survey to assess LLM adoption in industry for development tasks (N=84), and facilitated expert interviews to assess evolving data needs (N=10) in Q3 2023. In Q2 2024, we explored practitioners' current and anticipated LLM usage through a user study involving two LLM-based prototypes (N=12). While each study addressed distinct research goals, they revealed a broader narrative about evolving LLM usage in aggregate. We discovered an emerging shift in data understanding from heuristic-first, bottom-up approaches to insights-first, top-down workflows supported by LLMs. Furthermore, to respond to a more complex data landscape, data practitioners now supplement traditional subject-expert-created 'golden datasets' with LLM-generated 'silver' datasets and rigorously validated 'super golden' datasets curated by diverse experts. This research sheds light on the transformative role of LLMs in large-scale analysis of unstructured data and highlights opportunities for further tool development.

Deep learning has advanced medical image classification, but interpretability challenges hinder its clinical adoption. This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a multi-agent Retrieval-Augmented Generation (RAG) system for report generation. By modeling relationships between visual features and clinical concepts, we create interpretable concept vectors that guide a multi-agent RAG system to generate radiology reports, enhancing clinical relevance, explainability, and transparency. Evaluation of the generated reports using an LLM-as-a-judge confirmed the interpretability and clinical utility of our model's outputs. On the COVID-QU dataset, our model achieved 81% classification accuracy and demonstrated robust report generation performance, with five key metrics ranging between 84% and 90%. This interpretable multi-agent framework bridges the gap between high-performance AI and the explainability required for reliable AI-driven CXR analysis in clinical settings.

The increasing demand for privacy-preserving data analytics in finance necessitates solutions for synthetic data generation that rigorously uphold privacy standards. We introduce DP-Fed-FinDiff framework, a novel integration of Differential Privacy, Federated Learning and Denoising Diffusion Probabilistic Models designed to generate high-fidelity synthetic tabular data. This framework ensures compliance with stringent privacy regulations while maintaining data utility. We demonstrate the effectiveness of DP-Fed-FinDiff on multiple real-world financial datasets, achieving significant improvements in privacy guarantees without compromising data quality. Our empirical evaluations reveal the optimal trade-offs between privacy budgets, client configurations, and federated optimization strategies. The results affirm the potential of DP-Fed-FinDiff to enable secure data sharing and robust analytics in highly regulated domains, paving the way for further advances in federated learning and privacy-preserving data synthesis.

AI for Mathematics (AI4Math) is not only intriguing intellectually but also crucial for AI-driven discovery in science, engineering, and beyond. Extensive efforts on AI4Math have mirrored techniques in NLP, in particular, training large language models on carefully curated math datasets in text form. As a complementary yet less explored avenue, formal mathematical reasoning is grounded in formal systems such as proof assistants, which can verify the correctness of reasoning and provide automatic feedback. In this position paper, we advocate for formal mathematical reasoning and argue that it is indispensable for advancing AI4Math to the next level. In recent years, we have seen steady progress in using AI to perform formal reasoning, including core tasks such as theorem proving and autoformalization, as well as emerging applications such as verifiable generation of code and hardware designs. However, significant challenges remain to be solved for AI to truly master mathematics and achieve broader impact. We summarize existing progress, discuss open challenges, and envision critical milestones to measure future success. At this inflection point for formal mathematical reasoning, we call on the research community to come together to drive transformative advancements in this field.

There is a significant body of work looking at the ethical considerations of large language models (LLMs): critiquing tools to measure performance and harms; proposing toolkits to aid in ideation; discussing the risks to workers; considering legislation around privacy and security etc. As yet there is no work that integrates these resources into a single practical guide that focuses on LLMs; we attempt this ambitious goal. We introduce 'LLM Ethics Whitepaper', which we provide as an open and living resource for NLP practitioners, and those tasked with evaluating the ethical implications of others' work. Our goal is to translate ethics literature into concrete recommendations and provocations for thinking with clear first steps, aimed at computer scientists. 'LLM Ethics Whitepaper' distils a thorough literature review into clear Do's and Don'ts, which we present also in this paper. We likewise identify useful toolkits to support ethical work. We refer the interested reader to the full LLM Ethics Whitepaper, which provides a succinct discussion of ethical considerations at each stage in a project lifecycle, as well as citations for the hundreds of papers from which we drew our recommendations. The present paper can be thought of as a pocket guide to conducting ethical research with LLMs.

Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for effective interaction. Our work introduces a data-centric customization approach for efficiently enhancing multimodal understanding in conversational speech modeling. Central to our contributions is a novel multi-task learning paradigm that involves designing auxiliary tasks to utilize a small amount of speech data. Our approach achieves state-of-the-art performance on the Spoken-SQuAD benchmark, using only 10% of the training data with open-weight models, establishing a robust and efficient framework for audio-centric conversational modeling. We also introduce ASK-QA, the first dataset for multi-turn spoken dialogue with ambiguous user requests and dynamic evaluation inputs. Code and data forthcoming.

Arguments evoke emotions, influencing the effect of the argument itself. Not only the emotional intensity but also the category influence the argument's effects, for instance, the willingness to adapt stances. While binary emotionality has been studied in arguments, there is no work on discrete emotion categories (e.g., "Anger") in such data. To fill this gap, we crowdsource subjective annotations of emotion categories in a German argument corpus and evaluate automatic LLM-based labeling methods. Specifically, we compare three prompting strategies (zero-shot, one-shot, chain-of-thought) on three large instruction-tuned language models (Falcon-7b-instruct, Llama-3.1-8B-instruct, GPT-4o-mini). We further vary the definition of the output space to be binary (is there emotionality in the argument?), closed-domain (which emotion from a given label set is in the argument?), or open-domain (which emotion is in the argument?). We find that emotion categories enhance the prediction of emotionality in arguments, emphasizing the need for discrete emotion annotations in arguments. Across all prompt settings and models, automatic predictions show a high recall but low precision for predicting anger and fear, indicating a strong bias toward negative emotions.

This paper explores the potential of recurrent neural networks (RNNs) and other subquadratic architectures as competitive alternatives to transformer-based models in low-resource language modeling scenarios. We utilize HGRN2 (Qin et al., 2024), a recently proposed RNN-based architecture, and comparatively evaluate its effectiveness against transformer-based baselines and other subquadratic architectures (LSTM, xLSTM, Mamba). Our experimental results show that BABYHGRN, our HGRN2 language model, outperforms transformer-based models in both the 10M and 100M word tracks of the challenge, as measured by their performance on the BLiMP, EWoK, GLUE and BEAR benchmarks. Further, we show the positive impact of knowledge distillation. Our findings challenge the prevailing focus on transformer architectures and indicate the viability of RNN-based models, particularly in resource-constrained environments.

The rapid development of large language models (LLMs) has transformed many industries, including healthcare. However, previous medical LLMs have largely focused on leveraging general medical knowledge to provide responses, without accounting for patient variability and lacking true personalization at the individual level. To address this, we propose a novel method called personalized medical language model (PMLM), which explores and optimizes personalized LLMs through recommendation systems and reinforcement learning (RL). Specifically, by utilizing self-informed and peer-informed personalization, PMLM captures changes in behaviors and preferences to design initial personalized prompts tailored to individual needs. We further refine these initial personalized prompts through RL, ultimately enhancing the precision of LLM guidance. Notably, the personalized prompt are hard prompt, which grants PMLM high adaptability and reusability, allowing it to directly leverage high-quality proprietary LLMs. We evaluate PMLM using real-world obstetrics and gynecology data, and the experimental results demonstrate that PMLM achieves personalized responses, and it provides more refined and individualized services, offering a potential way for personalized medical LLMs.

In the software industry, the drive to add new features often overshadows the need to improve existing code. Large Language Models (LLMs) offer a new approach to improving codebases at an unprecedented scale through AI-assisted refactoring. However, LLMs come with inherent risks such as braking changes and the introduction of security vulnerabilities. We advocate for encapsulating the interaction with the models in IDEs and validating refactoring attempts using trustworthy safeguards. However, equally important for the uptake of AI refactoring is research on trust development. In this position paper, we position our future work based on established models from research on human factors in automation. We outline action research within CodeScene on development of 1) novel LLM safeguards and 2) user interaction that conveys an appropriate level of trust. The industry collaboration enables large-scale repository analysis and A/B testing to continuously guide the design of our research interventions.