Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised probes and Sparse Autoencoders (SAEs), or on output distribution inspection, such as logit-oriented approaches. A full understanding of LLM vector spaces, however, requires integrating both perspectives, something existing approaches struggle with due to constraints on latent feature definitions. We introduce the Hyperdimensional Probe, a hybrid supervised probe that combines symbolic representations with neural probing. Leveraging Vector Symbolic Architectures (VSAs) and hypervector algebra, it unifies prior methods: the top-down interpretability of supervised probes, SAE's sparsity-driven proxy space, and output-oriented logit investigation. This allows deeper input-focused feature extraction while supporting output-oriented investigation. Our experiments show that our method consistently extracts meaningful concepts across LLMs, embedding sizes, and setups, uncovering concept-driven patterns in analogy-oriented inference and QA-focused text generation. By supporting joint input-output analysis, this work advances semantic understanding of neural representations while unifying the complementary perspectives of prior methods.

Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation and self-harm are still unclear, hindered by the lack of unified crisis taxonomies and clinical evaluation standards. We address this by creating: (1) a taxonomy of six crisis categories; (2) a dataset of over 2,000 inputs from 12 mental health datasets, classified into these categories; and (3) a clinical response assessment protocol. We also use LLMs to identify crisis inputs and audit five models for response safety and appropriateness. First, we built a clinical-informed crisis taxonomy and evaluation protocol. Next, we curated 2,252 relevant examples from over 239,000 user inputs, then tested three LLMs for automatic classification. In addition, we evaluated five models for the appropriateness of their responses to a user's crisis, graded on a 5-point Likert scale from harmful (1) to appropriate (5). While some models respond reliably to explicit crises, risks still exist. Many outputs, especially in self-harm and suicidal categories, are inappropriate or unsafe. Different models perform variably; some, like gpt-5-nano and deepseek-v3.2-exp, have low harm rates, but others, such as gpt-4o-mini and grok-4-fast, generate more unsafe responses. All models struggle with indirect signals, default replies, and context misalignment. These results highlight the urgent need for better safeguards, crisis detection, and context-aware responses in LLMs. They also show that alignment and safety practices, beyond scale, are crucial for reliable crisis support. Our taxonomy, datasets, and evaluation methods support ongoing AI mental health research, aiming to reduce harm and protect vulnerable users.

Brownfield engineering work involving legacy systems, incomplete documentation, and fragmented architectural knowledge poses unique challenges for the effective use of large language models (LLMs). Prior research has largely focused on greenfield or synthetic tasks, leaving a gap in structured workflows for complex, context-heavy environments. This paper introduces the Discover-Define-Deliver (D3) Framework, a disciplined LLM-assisted workflow that combines role-separated prompting strategies with applied best practices for navigating ambiguity in brownfield systems. The framework incorporates a dual-agent prompting architecture in which a Builder model generates candidate outputs and a Reviewer model provides structured critique to improve reliability. I conducted an exploratory survey study with 52 software practitioners who applied the D3 workflow to real-world engineering tasks such as legacy system exploration, documentation reconstruction, and architectural refactoring. Respondents reported perceived improvements in task clarity, documentation quality, and cognitive load, along with self-estimated productivity gains. In this exploratory study, participants reported a weighted average productivity improvement of 26.9%, reduced cognitive load for approximately 77% of participants, and 83% of participants spent less time fixing or rewriting code due to better initial planning with AI. As these findings are self-reported and not derived from controlled experiments, they should be interpreted as preliminary evidence of practitioner sentiment rather than causal effects. The results highlight both the potential and limitations of structured LLM workflows for legacy engineering systems and motivate future controlled evaluations.

In the face of accelerating global urbanization and the increasing frequency of extreme weather events, highresolution urban rainfall monitoring is crucial for building resilient smart cities. Commercial Microwave Links (CMLs) are an emerging data source with great potential for this task.While traditional rainfall retrieval from CMLs relies on physicsbased models, these often struggle with real-world complexities like signal noise and nonlinear attenuation. To address these limitations, this paper proposes a novel hybrid deep learning architecture based on the Transformer and a Bidirectional Gated Recurrent Unit (BiGRU), which we name TabGRU. This design synergistically captures both long-term dependencies and local sequential features in the CML signal data. The model is further enhanced by a learnable positional embedding and an attention pooling mechanism to improve its dynamic feature extraction and generalization capabilities. The model was validated on a public benchmark dataset from Gothenburg, Sweden (June-September 2015). The evaluation used 12 sub-links from two rain gauges (Torp and Barl) over a test period (August 22-31) covering approximately 10 distinct rainfall events. The proposed TabGRU model demonstrated consistent advantages, outperforming deep learning baselines and achieving high coefficients of determination (R2) at both the Torp site (0.91) and the Barl site (0.96). Furthermore, compared to the physics-based approach, TabGRU maintained higher accuracy and was particularly effective in mitigating the significant overestimation problem observed in the PL model during peak rainfall events. This evaluation confirms that the TabGRU model can effectively overcome the limitations of traditional methods, providing a robust and accurate solution for CML-based urban rainfall monitoring under the tested conditions.

Prompt optimization has become crucial for enhancing the performance of large language models (LLMs) across a broad range of tasks. Although many research papers show its effectiveness, practical adoption is hindered as existing implementations are often tied to unmaintained and isolated research codebases. To address this, we introduce promptolution, a unified and modular open-source framework that provides all components required for prompt optimization within a single extensible system for both practitioners and researchers. It integrates multiple contemporary discrete prompt optimizers while remaining agnostic to the underlying LLM implementation.

Large language model (LLM) services now answer billions of queries per day, and industry reports show that inference, not training, accounts for more than 90% of total power consumption. However, existing benchmarks focus on either training/fine-tuning or performance of inference and provide little support for power consumption measurement and analysis of inference. We introduce TokenPowerBench, the first lightweight and extensible benchmark designed for LLM-inference power consumption studies. The benchmark combines (i) a declarative configuration interface covering model choice, prompt set, and inference engine, (ii) a measurement layer that captures GPU-, node-, and system-level power without specialized power meters, and (iii) a phase-aligned metrics pipeline that attributes energy to the prefill and decode stages of every request. These elements make it straight-forward to explore the power consumed by an LLM inference run; furthermore, by varying batch size, context length, parallelism strategy and quantization, users can quickly assess how each setting affects joules per token and other energy-efficiency metrics. We evaluate TokenPowerBench on four of the most widely used model series (Llama, Falcon, Qwen, and Mistral). Our experiments cover from 1 billion parameters up to the frontier-scale Llama3-405B model. Furthermore, we release TokenPowerBench as open source to help users to measure power consumption, forecast operating expenses, and meet sustainability targets when deploying LLM services.

This article investigates the modeling and control of Lagrangian systems involving non-conservative forces using a hybrid method that does not require acceleration calculations. It focuses in particular on the derivation and identification of physically consistent models, which are essential for model-based control synthesis. Lagrangian or Hamiltonian neural networks provide useful structural guarantees but the learning of such models often leads to inconsistent models, especially on real physical systems where training data are limited, partial and noisy. Motivated by this observation and the objective to exploit these models for model-based nonlinear control, a learning algorithm relying on an original loss function is proposed to improve the physical consistency of Lagrangian systems. A comparative analysis of different learning-based modeling approaches with the proposed solution shows significant improvements in terms of physical consistency of the learned models, on both simulated and experimental systems. The model's consistency is then exploited to demonstrate, on an experimental benchmark, the practical relevance of the proposed methodology for feedback linearization and energy-based control techniques.

The rapid advancement and adaptability of Large Language Models (LLMs) highlight the need for moral consistency, the capacity to maintain ethically coherent reasoning across varied contexts. Existing alignment frameworks, structured approaches designed to align model behavior with human ethical and social norms, often rely on static datasets and post-hoc evaluations, offering limited insight into how ethical reasoning may evolve across different contexts or temporal scales. This study presents the Moral Consistency Pipeline (MoCoP), a dataset-free, closed-loop framework for continuously evaluating and interpreting the moral stability of LLMs. MoCoP combines three supporting layers: (i) lexical integrity analysis, (ii) semantic risk estimation, and (iii) reasoning-based judgment modeling within a self-sustaining architecture that autonomously generates, evaluates, and refines ethical scenarios without external supervision. Our empirical results on GPT-4-Turbo and DeepSeek suggest that MoCoP effectively captures longitudinal ethical behavior, revealing a strong inverse relationship between ethical and toxicity dimensions (correlation rET = -0.81, p value less than 0.001) and a near-zero association with response latency (correlation rEL approximately equal to 0). These findings demonstrate that moral coherence and linguistic safety tend to emerge as stable and interpretable characteristics of model behavior rather than short-term fluctuations. Furthermore, by reframing ethical evaluation as a dynamic, model-agnostic form of moral introspection, MoCoP offers a reproducible foundation for scalable, continuous auditing and advances the study of computational morality in autonomous AI systems.

Thinking Large Language Models (LLMs) used as judges for pairwise preferences remain noisy at the single-sample level, and common aggregation rules (majority vote, soft self-consistency, or instruction-based self-aggregation) are inconsistent when ties are allowed. We study inference-time compute (ITC) for evaluators that generate n independent thinking-rating samples per item, and propose a principled, distribution-calibrated aggregation scheme. Our method models three-way preferences with a Bradley-Terry-Davidson formulation on rating counts, leveraging both polarity (margin among non-ties) and decisiveness (non-tie rate) to distinguish narrow margins from strong consensus. Across various evaluation benchmarks, our approach consistently reduces MAE and increases pairwise accuracy versus standard baselines, and when evaluated against human-consensus meta-labels, matches or exceeds individual human raters. These results show that carefully allocating ITC and aggregating with distribution-aware methods turns noisy individual model judgments into reliable ratings for evaluation. Thinking large language models (LLMs) are increasingly being employed as automated judges for evaluating the output of other generative systems, a paradigm known as "Thinking-LLM-as-a-Judge" (Saha et al., 2025). This approach offers a scalable and cost-effective alternative to human evaluation, which is often slow and expensive. To mitigate the inherent stochasticity and noise of single-pass judgments, a common strategy is to leverage inference-time compute (ITC) Snell et al. (2024) by generating multiple independent reasoning and rating samples for each item being evaluated. However, the reliability of the final judgment hinges critically on how these multiple outputs are aggregated. Current aggregation methods, such as majority voting (Self-Consistency (Wang et al., 2023b)) or heuristics based on model confidence scores or LLM generated aggregators, are often brittle and statistically suboptimal.

Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, and input/output filtering. Despite good results, LLMs remain susceptible to abuse, and jailbreak probability increases with context length. There is a need for robust LLM security guarantees in long-context situations. We propose control sentences inserted into the LLM context as invasive context engineering to partially solve the problem. We suggest this technique can be generalized to the Chain-of-Thought process to prevent scheming. Invasive Context Engineering does not rely on LLM training, avoiding data shortage pitfalls which arise in training models for long context situations.