In this study, we investigate the use of large language models (LLMs), specifically ChatGPT, for structured deductive qualitative coding. While most current research emphasizes inductive coding applications, we address the underexplored potential of LLMs to perform deductive classification tasks aligned with established human-coded schemes. Using the Comparative Agendas Project (CAP) Master Codebook, we classified U.S. Supreme Court case summaries into 21 major policy domains. We tested four intervention methods: zero-shot, few-shot, definition-based, and a novel Step-by-Step Task Decomposition strategy, across repeated samples. Performance was evaluated using standard classification metrics (accuracy, F1-score, Cohen's kappa, Krippendorff's alpha), and construct validity was assessed using chi-squared tests and Cramer's V. Chi-squared and effect size analyses confirmed that intervention strategies significantly influenced classification behavior, with Cramer's V values ranging from 0.359 to 0.613, indicating moderate to strong shifts in classification patterns. The Step-by-Step Task Decomposition strategy achieved the strongest reliability (accuracy = 0.775, kappa = 0.744, alpha = 0.746), achieving thresholds for substantial agreement. Despite the semantic ambiguity within case summaries, ChatGPT displayed stable agreement across samples, including high F1 scores in low-support subclasses. These findings demonstrate that with targeted, custom-tailored interventions, LLMs can achieve reliability levels suitable for integration into rigorous qualitative coding workflows.

Brain foundation models represent a new frontier in AI: instead of processing text or images, these models interpret real-time neural signals from EEG, fMRI, and other neurotechnologies. When integrated with brain-computer interfaces (BCIs), they may enable transformative applications-from thought controlled devices to neuroprosthetics-by interpreting and acting on brain activity in milliseconds. However, these same systems pose unprecedented risks, including the exploitation of subconscious neural signals and the erosion of cognitive liberty. Users cannot easily observe or control how their brain signals are interpreted, creating power asymmetries that are vulnerable to manipulation. This paper proposes embedding fiduciary duties-loyalty, care, and confidentiality-directly into BCI-integrated brain foundation models through technical design. Drawing on legal traditions and recent advancements in AI alignment techniques, we outline implementable architectural and governance mechanisms to ensure these systems act in users' best interests. Placing brain foundation models on a fiduciary footing is essential to realizing their potential without compromising self-determination.

Accurate prediction of critical heat flux (CHF) is an essential component of safety analysis in pressurized and boiling water reactors. To support reliable prediction of this quantity, several empirical correlations and lookup tables have been constructed from physical experiments over the past several decades. With the onset of accessible machine learning (ML) frameworks, multiple initiatives have been established with the goal of predicting CHF more accurately than these traditional methods. While purely data-driven surrogate modeling has been extensively investigated, these approaches lack interpretability, lack resilience to data scarcity, and have been developed mostly using data from tube experiments. As a result, bias-correction hybrid approaches have become increasingly popular, which correct initial "low-fidelity" estimates provided by deterministic base models by using ML-predicted residuals. This body of work has mostly considered round tube geometries; annular geometry-specific ML models have not yet been deployed in thermal hydraulic codes. This study developed, deployed, and validated four ML models to predict CHF in annular geometries using the CTF subchannel code. Three empirical correlation models, Biasi, Bowring, and Katto, were used as base models for comparison. The ML models were trained and tested using 577 experimental annulus data points from four datasets: Becker, Beus, Janssen, and Mortimore. Baseline CHF predictions were obtained from the empirical correlations, with mean relative errors above 26%. The ML-driven models achieved mean relative errors below 3.5%, with no more than one point exceeding the 10% error envelope. In all cases, the hybrid ML models significantly outperformed their empirical counterparts.

While Artificial Intelligence (AI) is not a new field, recent developments, especially with the release of generative tools like ChatGPT, have brought it to the forefront of the minds of industry workers and academic folk alike. There is currently much talk about AI and its ability to reshape many everyday processes as we know them through automation. It also allows users to expand their ideas by suggesting things they may not have thought of on their own and provides easier access to information. However, not all of the changes this technology will bring or has brought so far are positive; this is why it is extremely important for all modern people to recognize and understand the risks before using these tools and allowing them to cause harm. This work takes a position on better understanding many equity concerns and the spread of misinformation that result from new AI, in this case, specifically ChatGPT and deepfakes, and encouraging collaboration with law enforcement, developers, and users to reduce harm. Considering many academic sources, it warns against these issues, analyzing their cause and impact in fields including healthcare, education, science, academia, retail, and finance. Lastly, we propose a set of future-facing guidelines and policy considerations to solve these issues while still enabling innovation in these fields, this responsibility falling upon users, developers, and government entities.

Large language models (LLMs) are increasingly being used in user-facing applications, from providing medical consultations to job interview advice. Recent research suggests that these models are becoming increasingly proficient at inferring identity information about the author of a piece of text from linguistic patterns as subtle as the choice of a few words. However, little is known about how LLMs use this information in their decision-making in real-world applications. We perform the first comprehensive analysis of how identity markers present in a user's writing bias LLM responses across five different high-stakes LLM applications in the domains of medicine, law, politics, government benefits, and job salaries. We find that LLMs are extremely sensitive to markers of identity in user queries and that race, gender, and age consistently influence LLM responses in these applications. For instance, when providing medical advice, we find that models apply different standards of care to individuals of different ethnicities for the same symptoms; we find that LLMs are more likely to alter answers to align with a conservative (liberal) political worldview when asked factual questions by older (younger) individuals; and that LLMs recommend lower salaries for non-White job applicants and higher salaries for women compared to men. Taken together, these biases mean that the use of off-the-shelf LLMs for these applications may cause harmful differences in medical care, foster wage gaps, and create different political factual realities for people of different identities. Beyond providing an analysis, we also provide new tools for evaluating how subtle encoding of identity in users' language choices impacts model decisions. Given the serious implications of these findings, we recommend that similar thorough assessments of LLM use in user-facing applications are conducted before future deployment.

--This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to fully unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a bayesian formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. COUSTIC waves propagation in enclosed environments is significantly influenced by reflections and diffractions from surrounding surfaces and objects. These interactions alter the original waveform and result in reverberation, which can be modeled as a superposition of delayed and attenuated versions of the source signal. Reverberation has long been recognized as a critical factor affecting speech intelligibility [1], and its detrimental effects on audio clarity have motivated decades of research. The task of reverberation suppression, commonly referred to as dereverberation, has received renewed attention in recent years due to its relevance in a wide range of audio processing applications. Effective dereverberation is essential in enhancing the performance of hearing aids [2], improving communication quality in hands-free [3] telephony, and enabling robust Automatic Speech Recognition (ASR) in human-machine interaction scenarios [4]. It also serves as a key preprocessing step in general-purpose speech enhancement frameworks [5]. Beyond suppression, reverberation itself plays a constructive role in audio production, particularly in simulating desired acoustic characteristics in post-processing. Reverberation conversion, or acoustic transfer, aims to transform a given recording, possibly containing unknown or undesired room effects, into a version consistent with a target acoustic environment. This work was funded by the European Union (ERC, HI-Audio, 101052978). Views and opinions expressed are however those of the authors only and do not necessarily reflect those of the European Union or the European Research Council.

This study explores the relationship between voter trust and their experiences during elections by applying a rule-based data mining technique to the 2022 Survey of the Performance of American Elections (SPAE). Using the Apriori algorithm and setting parameters to capture meaningful associations (support >= 3%, confidence >= 60%, and lift > 1.5), the analysis revealed a strong connection between demographic attributes and voting-related challenges, such as registration hurdles, accessibility issues, and queue times. For instance, respondents who indicated that accessing polling stations was "very easy" and who reported moderate confidence were found to be over six times more likely (lift = 6.12) to trust their county's election outcome and experience no registration issues. A further analysis, which adjusted the support threshold to 2%, specifically examined patterns among minority voters. It revealed that 98.16 percent of Black voters who reported easy access to polling locations also had smooth registration experiences. Additionally, those who had high confidence in the vote-counting process were almost two times as likely to identify as Democratic Party supporters. These findings point to the important role that enhancing voting access and offering targeted support can play in building trust in the electoral system, particularly among marginalized communities.

Explainable intrusion detection systems (IDS) are now recognized as essential for mission-critical networks, yet most "XAI" pipelines still bolt an approximate explainer onto an opaque classifier, leaving analysts with partial and sometimes misleading insights. The Interpretable Generalization (IG) mechanism, published in IEEE Transactions on Information Forensics and Security, eliminates that bottleneck by learning coherent patterns - feature combinations unique to benign or malicious traffic - and turning them into fully auditable rules. IG already delivers outstanding precision, recall, and AUC on NSL-KDD, UNSW-NB15, and UKM-IDS20, even when trained on only 10% of the data. To raise precision further without sacrificing transparency, we introduce Multi-Granular Discretization (IG-MD), which represents every continuous feature at several Gaussian-based resolutions. On UKM-IDS20, IG-MD lifts precision by greater than or equal to 4 percentage points across all nine train-test splits while preserving recall approximately equal to 1.0, demonstrating that a single interpretation-ready model can scale across domains without bespoke tuning.

The automated summarisation of parliamentary debates using large language models (LLMs) offers a promising way to make complex legislative discourse more accessible to the public. However, such summaries must not only be accurate and concise but also equitably represent the views and contributions of all speakers. This paper explores the use of LLMs to summarise plenary debates from the European Parliament and investigates the algorithmic and representational biases that emerge in this context. We propose a structured, multi-stage summarisation framework that improves textual coherence and content fidelity, while enabling the systematic analysis of how speaker attributes -- such as speaking order or political affiliation -- influence the visibility and accuracy of their contributions in the final summaries. Through our experiments using both proprietary and open-weight LLMs, we find evidence of consistent positional and partisan biases, with certain speakers systematically under-represented or misattributed. Our analysis shows that these biases vary by model and summarisation strategy, with hierarchical approaches offering the greatest potential to reduce disparity. These findings underscore the need for domain-sensitive evaluation metrics and ethical oversight in the deployment of LLMs for democratic applications.

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As sequence lengths increase, the number of Key-Value (KV) pairs in LLMs escalates, creating a significant efficiency bottleneck. In this paper, we propose a new KV cache optimization paradigm called LaCache, a training-free method for efficient and accurate generative inference of LLMs. LaCache enables LLMs to simultaneously address both of the critical challenges in long-range modeling: robust long-range capabilities and continuous generation without running out-of-memory (OOM). Specifically, LaCache integrates two key innovations: (1) a ladder-shaped KV cache pattern that stores KV pairs not only sequentially (left-to-right within each layer) but also across layers (from shallow to deep), providing an extended span for capturing long-range dependencies under a fixed storage budget, thereby boosting long-range capabilities; and (2) an iterative compaction mechanism that progressively compresses older caches, freeing up space for new tokens within a fixed cache size. This token distance-based dynamic compression enables more effective continuous generation under constrained cache budgets. Experiments across various tasks, benchmarks, and LLM models consistently validate LaCache's effectiveness in enhancing LLMs' long-range capabilities. Our code is available at https://github.com/GATECH-EIC/LaCache.