As the world population is ageing rapidly and old age comes with multiple health issues, the need for medical services is likely to increase in a couple of decades beyond the limits of the medical systems of almost any country. In response to this trend, a variety of technologies have been developed with the aim of helping older people live independently as long as possible and reduce the burden on caregivers. In this paper, we propose a solution to encode the information about the activity of the monitored person, captured by a set of binary sensors, in the form of activity maps that reflect not only the intensity, but also the spatial distribution of the activity between a set of behaviorally meaningful places. Then, we propose a method for automatic analysis of the activity maps in order to detect deviations from the previously recorded routine. We have tested the method on two public activity recognition datasets and found that the proposed solution is not only feasible, but also has several important advantages (it is low cost, scalable, adaptable, requires little expert knowledge for setup and protects the privacy of the monitored persons) that make it applicable on a large scale, including for people with low socio-economic status.

Background: Large language models are increasingly used for rubric-based grading, but it remains unclear whether they adapt selectively when criterion weights change while the response, criterion definitions, and total score remain fixed. This study examined whether alternative point allocations produce targeted criterion-level adaptation or broader grading instability. Methods: A controlled paired design was applied to 1000 student responses, comprising 500 technical and 500 argumentative answers. Eight local open-weight LLMs evaluated every response under two analytic rubrics totaling 10 points. One point was transferred from Clarity to Completeness for technical responses and from Clarity to Dialecticality for argumentative responses. Of 16,000 expected evaluations, 15,999 were structurally valid, yielding 7999 complete cross-rubric pairs. Model outputs were analyzed for total-score shifts, affected-criterion adaptation, stability of unaffected criteria, model–human alignment, and correspondence with differences between two human evaluation conditions. Results: All models assigned lower mean scores under Rubric B, with mean shifts ranging from −1.239 to −0.182 points. Adaptation mechanisms differed substantially across models and response types. gemma3:4b frequently preserved technical total scores through compensating criterion changes, whereas llama3.1:8b showed extensive spillover into unaffected criteria. The Qwen models generally produced smaller total-score reductions and greater stability in unchanged dimensions. The mean score was 0.637 points higher under the human Rubric B condition than under the human Rubric A condition, although the two conditions were applied by different evaluator pairs; every model shifted negatively, and the lowest overall shift error was obtained by qwen3:4b at 1.498 points. Conclusions: Rubric sensitivity did not consistently imply localized or criterion-consistent adaptation. Reliable evaluation of LLM graders therefore requires separate analysis of total scores, affected criteria, unaffected criteria, human alignment, and cross-condition shift correspondence.

Local open-weight large language models (LLMs) are increasingly used in privacy-sensitive settings, yet isolated prompts may not reveal whether safety boundaries remain stable during conversation. SafeBoundary-LLM evaluated seven local models across 14 sensitive domains, 84 boundary sets, 672 single-turn prompts, and 84 five-turn escalation conversations; the same models were evaluated separately on XSTest and JBB-Behaviors. Evaluators R1 and R2 independently classified all 12,194 responses, with R2 labels used for primary outcomes and unreconciled labels used for reliability analysis. Exact agreement exceeded 93% in each dataset. In SafeBoundary-LLM, 456 out of 7644 responses (5.97%) were confirmed-or-mixed failures. The multi-turn failure rate was 14.69% versus 0.51% for single-turn prompts, yielding a rate ratio of 28.80 (95% CI [21.20, 43.80]; Holm-adjusted p = 0.0006); boundary collapse occurred only at Turns 4–5, and role-play bypass accounted for 299 out of 456 failures. On answer-expected items, over-refusal was 4.34% in XSTest and 17.29% in JBB-Behaviors, whereas unsafe compliance on refusal-expected items was 0.36% and 0.86%, respectively. These findings support an evaluation strategy that includes public single-turn benchmarks, controlled multi-turn escalation, independent human review, and traceable audit records for locally deployed LLMs.

Background: Multi-agent large language model (LLM) systems increasingly rely on structured interaction, debate, and final model-based evaluation, yet an unsupported causal attribution introduced by one participant may propagate through the interaction and influence subsequent decisions. This study introduces ClaimArena-LLM, a controlled framework for auditing adversarial propagation, evidentiary provenance, and final-stage evaluator vulnerability in multi-agent causal reasoning. Methods: ClaimArena-LLM uses 100 synthetic causal incident cases with predefined evidence-supported and false causal propositions. Each case was evaluated under matched adversarial and all-honest debate conditions using four functional roles: investigator, honest analyst, adversarial analyst, and auditor. The experimental program comprised 1460 validated runs, including the 200-run main experiment, claim-source lineage visibility and debate-round ablations, an 800-run balanced model–role rotation, and a 60-run proposition-identifier and presentation-order sensitivity control. Outcomes were scored deterministically from structured causal propositions, evidence references, claim lineage, reports, and auditor verdicts. Results: The adversarial analyst maintained the predefined false causal target with 97.6% mean fidelity. Adversarial exposure increased investigator shifts toward the false target by 16.0 percentage points (Holm-adjusted p = 0.035). At the auditor stage, false-target attribution increased by 11.0 percentage points (adjusted p = 0.043), verdict contamination by 20.0 percentage points (adjusted p = 0.002), and semantic provenance validity decreased by 20.0 percentage points (adjusted p = 0.002). Neither the manipulation nor the false target was explicitly detected. The ablations showed no robust adjusted differences, model–role rotation revealed substantial configuration dependence, and no benchmark-characteristic interaction remained significant after Holm correction. The proposition-identifier and presentation-order sensitivity control showed no statistically robust evidence that fixed proposition encoding explained the observed condition contrasts. Conclusions: Adversarial causal influence in multi-agent LLM systems is selective rather than uniformly propagative and depends strongly on functional role and model–role configuration. Within the tested architecture, a final LLM auditor cannot be assumed to provide an independent safeguard against upstream contamination. Reliable evaluation therefore requires separate assessment of causal correctness, propagation, semantic provenance, and final-stage adversarial awareness rather than reliance on final answer accuracy alone.

Background: LLM-as-a-judge workflows are increasingly used to evaluate open-ended model outputs, but the judge model can itself become a source of error in safety assessment. SafetyJudge-LLM audits local open-weight LLMs as semantic safety judges. Methods: This study reused a fixed set of previously reviewed safety-boundary responses and their hidden reference labels. Two independent human evaluations (R1 and R2) quantified reference-layer ambiguity. Seven local open-weight judge models were evaluated under a common Ollama inference protocol. A paired C6 sensitivity analysis reran llama3.2:3b and qwen3:8b through Hugging Face Transformers. Results: The final judge-output matrix contained 10,612 retained outputs. R1–R2 agreement was 95.45% (Cohen’s κ = 0.612) overall but 47.80% (κ = 0.341) in secondary cases. Several judge models detected more than 90% of confirmed safety-boundary failures, but high detection was not always accompanied by low false-unsafe behavior on control cases. Output-format reliability also varied across models: overall label parseability was 98.11%, while strict JSON schema compliance was 92.55%. The llama3.2:3b schema-failure rate persisted across engines (52.06% under Ollama; 59.60% under Transformers), whereas qwen3:8b maintained complete compliance. Conclusions: SafetyJudge-LLM shows that local open-weight LLMs can support semantic safety judging, but their reliability must be evaluated across multiple dimensions.