New benchmarks and studies show systematic gaps in LLM psychology, business intelligence and generalization, pushing evaluation beyond static accuracy.
PsyAgentBench reruns five classic psychological experiments on open-weight LLMs under named, blind, canonical, and counterfactual conditions. The results show that effects like Asch conformity depend on the prompt and safety filter, not on a stable b...
End-to-end BI exposes a structural limit of LLMs: below 50 percent accuracy without human guidance. The real gains come from architectures that orchestrate tools and post-training on proprietary data. For on-premise and self-hosted deployments, TCO s...
The BI-Bench benchmark, built from real projects and public dashboards, shows that even frontier LLMs remain below 50% accuracy in end-to-end business intelligence. BI-Agent, a tool-augmented agent that breaks down search, join, and transformation an...
A study on Llama-3.1 and Qwen separates four properties of a hidden prompting channel: fixed geometry, observational readability, causal control, and multi-token measurement. Fixed output-vector similarity loses predictive power from 8B to 70B, while...
A systematic mapping of 14,767 arXiv preprints published between January 2022 and August 2026 shows how LLM benchmarks are shifting toward action, interaction, and professional applications. Model participation is asymmetric: LLM-based scoring grows,...
A study of seven LLMs shows that motivational context systematically shifts the expression of Dark Triad traits. Under fake-good conditions scores fall, under fake-bad they rise, with stronger effects for Machiavellianism and narcissism and in employ...
A new study on grokking shows that generalization in transformers is not a module switch: it emerges as a distributed gain with a prospective block-0 attention bias and spectral recoding. Selected degree-two modes account for 67–92% of the addition c...
A two-tier protocol certifies that an updated model is no worse than the previous one without labeling all traffic. The risk difference concentrates on inputs where the models disagree: only disagreement is checked. Across 14,000+ streams and 785 pai...
