Large language model (LLM)-powered chatbots are increasingly used for opinion exploration. Prior research examined how LLMs alter user views, yet little work extended beyond one-way influence to address how user input can affect LLM responses and how such bi-directional influence manifests throughout the multi-turn conversations. This study investigates this dynamic through 50 controversial-topic discussions with participants (N=266) across three conditions: static statements, standard chatbot, and personalized chatbot. Results show that human opinions barely shifted, while LLM outputs changed more substantially, narrowing the gap between human and LLM stance. Personalization amplified these shifts in both directions compared to the standard setting. Analysis of multi-turn conversations further revealed that exchanges involving participants' personal stories were most likely to trigger stance changes for both humans and LLMs. Our work highlights the risk of over-alignment in human-LLM interaction and the need for careful design of personalized chatbots to more thoughtfully and stably align with users.

This doctoral thesis improves the transfer learning for sequence labeling tasks by adapting pre-trained neural language models. The proposed improvements in transfer learning involve introducing a multi-task model that incorporates an additional signal, a method based on architectural modifications in autoregressive large language models, and a sequence labeling framework for autoregressive large language models utilizing supervised in-context fine-tuning combined with response-oriented adaptation strategies. The first improvement is given in the context of domain transfer for the event trigger detection task. The domain transfer of the event trigger detection task can be improved by incorporating an additional signal obtained from a domain-independent text processing system into a multi-task model. The second improvement involves modifying the model's architecture. For that purpose, a method is proposed to enable bidirectional information flow across layers of autoregressive large language models. The third improvement utilizes autoregressive large language models as text generators through a generative supervised in-context fine-tuning framework. The proposed model, method, and framework demonstrate that pre-trained neural language models achieve their best performance on sequence labeling tasks when adapted through targeted transfer learning paradigms.

Radio Frequency Identification (RFID) tracking may be a viable solution for defense assets that must be stored in accordance with security guidelines. However, poor sensor specificity (vulnerabilities include long range detection, spoofing, and counterfeiting) can lead to erroneous detection and operational security events. We present a supervised learning simulation with realistic Received Signal Strength Indicator (RSSI) data and Decision Tree classification in a Computer Assisted Design (CAD)-modeled floor plan that encapsulates some of the challenges encountered in defense storage. In this work, we focused on classifying 12 lab zones (LabZoneA-L) to perform location inference. The raw dataset had approximately 980,000 reads. Class frequencies were imbalanced, and class weights were calculated to account for class imbalance in this multi-class setting. The model, trained on stratified subsamples to 5,000 balanced observations, yielded an overall accuracy of 34.2% and F1-scores greater than 0.40 for multiple zones (Zones F, G, H, etc.). However, rare classes (most notably LabZoneC) were often misclassified, even with the use of class weights. An adjacency-aware confusion matrix was calculated to allow better interpretation of physically adjacent zones. These results suggest that RSSI-based decision trees can be applied in realistic simulations to enable zone-level anomaly detection or misplacement monitoring for defense supply logistics. Reliable classification performance in low-coverage and low-signal zones could be improved with better antenna placement or additional sensors and sensor fusion with other modalities.

Generative Artificial Intelligence (GenAI) presents transformative opportunities for organizations, yet both midsize organizations and larger enterprises face distinctive adoption challenges. Midsize organizations encounter resource constraints and limited AI expertise, while enterprises struggle with organizational complexity and coordination challenges. Existing technology adoption frameworks, including TAM (Technology Acceptance Model), TOE (Technology Organization Environment), and DOI (Diffusion of Innovations) theory, lack the specificity required for GenAI implementation across these diverse contexts, creating a critical gap in adoption literature. This paper introduces FAIGMOE (Framework for the Adoption and Integration of Generative AI in Midsize Organizations and Enterprises), a conceptual framework addressing the unique needs of both organizational types. FAIGMOE synthesizes technology adoption theory, organizational change management, and innovation diffusion perspectives into four interconnected phases: Strategic Assessment, Planning and Use Case Development, Implementation and Integration, and Operationalization and Optimization. Each phase provides scalable guidance on readiness assessment, strategic alignment, risk governance, technical architecture, and change management adaptable to organizational scale and complexity. The framework incorporates GenAI specific considerations including prompt engineering, model orchestration, and hallucination management that distinguish it from generic technology adoption frameworks. As a perspective contribution, FAIGMOE provides the first comprehensive conceptual framework explicitly addressing GenAI adoption across midsize and enterprise organizations, offering actionable implementation protocols, assessment instruments, and governance templates requiring empirical validation through future research.

Abstract-- Accurate robot kinematics is essential for precise tool placement in articulated robots, but non-geometric factors can introduce configuration-dependent model discrepancies. This paper presents a configuration-dependent kinematic calibration framework for improving accuracy across the entire workspace. Local Product-of-Exponential (POE) models, selected for their parameterization continuity, are identified at multiple configurations and interpolated into a global model. Inspired by joint gravity load expressions, we employ Fourier basis function interpolation parameterized by the shoulder and elbow joint angles, achieving accuracy comparable to neural network and autoencoder methods but with substantially higher training efficiency. V alidation on two 6-DoF industrial robots shows that the proposed approach reduces the maximum positioning error by over 50%, meeting the sub-millimeter accuracy required for cold spray manufacturing. Robots with larger configuration-dependent discrepancies benefit even more. A dual-robot collaborative task demonstrates the framework's practical applicability and repeatability.

''Noisy'' datasets (regimes with low signal to noise ratios, small sample sizes, faulty data collection, etc) remain a key research frontier for classification methods with both theoretical and practical implications. We introduce FINDER, a rigorous framework for analyzing generic classification problems, with tailored algorithms for noisy datasets. FINDER incorporates fundamental stochastic analysis ideas into the feature learning and inference stages to optimally account for the randomness inherent to all empirical datasets. We construct ''stochastic features'' by first viewing empirical datasets as realizations from an underlying random field (without assumptions on its exact distribution) and then mapping them to appropriate Hilbert spaces. The Kosambi-Karhunen-Loéve expansion (KLE) breaks these stochastic features into computable irreducible components, which allow classification over noisy datasets via an eigen-decomposition: data from different classes resides in distinct regions, identified by analyzing the spectrum of the associated operators. We validate FINDER on several challenging, data-deficient scientific domains, producing state of the art breakthroughs in: (i) Alzheimer's Disease stage classification, (ii) Remote sensing detection of deforestation. We end with a discussion on when FINDER is expected to outperform existing methods, its failure modes, and other limitations.

Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason correctly. Current validation practices focus on predictive accuracy or computational efficiency, leaving the logical integrity of analytical conclusions untested. This study introduces the Analytical Reliability Benchmark (ARB), a reproducible framework that quantifies reasoning reliability in large language models applied to energy system analysis. The benchmark integrates five submetrics: accuracy, reasoning reliability, uncertainty discipline, policy consistency, and transparency, and evaluates model performance across deterministic, probabilistic, and epistemic scenarios using open technoeconomic datasets (NREL ATB 2024, DOE H2A/H2New, IEA WEO 2024). Four frontier models (GPT-4/5, Claude 4.5 Sonnet, Gemini 2.5 Pro, Llama 3 70B) were tested under identical factual and regulatory conditions. Results show that reasoning reliability can be objectively measured. GPT-4/5 and Claude 4.5 Sonnet achieved consistent and policy-compliant reasoning (Analytical Reliability Index greater than 90), Gemini 2.5 Pro demonstrated moderate stability, and Llama 3 70B remained below professional thresholds. Statistical validation confirmed that these differences are significant and reproducible. The ARB establishes the first quantitative method in the energy literature for verifying causal, probabilistic, and policy-driven reasoning in artificial intelligence systems, providing a reference framework for trustworthy and transparent analytical applications in the global energy transition.

Multi-class wine classification presents fundamental trade-offs between model accuracy, feature dimensionality, and interpretability - critical factors for production deployment in analytical chemistry. This paper presents a comprehensive empirical study of One-vs-Rest logistic regression on the UCI Wine dataset (178 samples, 3 cultivars, 13 chemical features), comparing from-scratch gradient descent implementation against scikit-learn's optimized solvers and quantifying L1 regularization effects on feature sparsity. Manual gradient descent achieves 92.59 percent mean test accuracy with smooth convergence, validating theoretical foundations, though scikit-learn provides 24x training speedup and 98.15 percent accuracy. Class-specific analysis reveals distinct chemical signatures with heterogeneous patterns where color intensity varies dramatically (0.31 to 16.50) across cultivars. L1 regularization produces 54-69 percent feature reduction with only 4.63 percent accuracy decrease, demonstrating favorable interpretability-performance trade-offs. We propose an optimal 5-feature subset achieving 62 percent complexity reduction with estimated 92-94 percent accuracy, enabling cost-effective deployment with 80 dollars savings per sample and 56 percent time reduction. Statistical validation confirms robust generalization with sub-2ms prediction latency suitable for real-time quality control. Our findings provide actionable guidelines for practitioners balancing comprehensive chemical analysis against targeted feature measurement in resource-constrained environments.

Deep Research (DR) agents built on Large Language Models (LLMs) can perform complex, multi-step research by decomposing tasks, retrieving online information, and synthesizing detailed reports. However, the misuse of LLMs with such powerful capabilities can lead to even greater risks. This is especially concerning in high-stakes and knowledge-intensive domains such as biosecurity, where DR can generate a professional report containing detailed forbidden knowledge. Unfortunately, we have found such risks in practice: simply submitting a harmful query, which a standalone LLM directly rejects, can elicit a detailed and dangerous report from DR agents. This highlights the elevated risks and underscores the need for a deeper safety analysis. Yet, jailbreak methods designed for LLMs fall short in exposing such unique risks, as they do not target the research ability of DR agents. To address this gap, we propose two novel jailbreak strategies: Plan Injection, which injects malicious sub-goals into the agent's plan; and Intent Hijack, which reframes harmful queries as academic research questions. We conducted extensive experiments across different LLMs and various safety benchmarks, including general and biosecurity forbidden prompts. These experiments reveal 3 key findings: (1) Alignment of the LLMs often fail in DR agents, where harmful prompts framed in academic terms can hijack agent intent; (2) Multi-step planning and execution weaken the alignment, revealing systemic vulnerabilities that prompt-level safeguards cannot address; (3) DR agents not only bypass refusals but also produce more coherent, professional, and dangerous content, compared with standalone LLMs. These results demonstrate a fundamental misalignment in DR agents and call for better alignment techniques tailored to DR agents. Code and datasets are available at https://chenxshuo.github.io/deeper-harm.

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to assess the safety of user inputs before generating final responses. The powerful reasoning ability can analyze the intention of the input query and will refuse to assist once it detects the harmful intent hidden by the jailbreak methods. Such guardrails have shown a significant boost in defense, such as the near-perfect refusal rates on the open-source gpt-oss series. Unfortunately, we find that these powerful reasoning-based guardrails can be extremely vulnerable to subtle manipulation of the input prompts, and once hijacked, can lead to even more harmful results. Specifically, we first uncover a surprisingly fragile aspect of these guardrails: simply adding a few template tokens to the input prompt can successfully bypass the seemingly powerful guardrails and lead to explicit and harmful responses. To explore further, we introduce a bag of jailbreak methods that subvert the reasoning-based guardrails. Our attacks span white-, gray-, and black-box settings and range from effortless template manipulations to fully automated optimization. Along with the potential for scalable implementation, these methods also achieve alarmingly high attack success rates (e.g., exceeding 90% across 5 different benchmarks on gpt-oss series on both local host models and online API services). Evaluations across various leading open-source LRMs confirm that these vulnerabilities are systemic, underscoring the urgent need for stronger alignment techniques for open-sourced LRMs to prevent malicious misuse. Code is open-sourced at https://chenxshuo.github.io/bag-of-tricks.