arXiv:2607. 20768v1 Announce Type: cross Abstract: Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are used to choose which models to combine.
arXiv:2608. 04618v1 Announce Type: new Abstract: Heterogeneous language-model ensembles expand the space of candidate responses, yet they lack a principled criterion for when a newly generated answer should supersede an already supported one.
The study evaluates how sixteen language models from ten families generate diverse formulations of a psychotherapeutic case, finding an average semantic diversity of 1.69 distinct formulations versus 1.43 for a single-model baseline. It introduces the Vendi Score to quantify diversity and defines a per-model dissent metric to identify the most divergent voice within an ensemble. The analysis shows that model identity significantly influences dissent, but this effect varies across model pairs and panel compositions, indicating that ensemble dispersion is a measurable property rather than an assumed one.
arXiv:2608. 06940v1 Announce Type: new Abstract: LLM judge panels are a standard evaluation tool, but prior work reports highly correlated panel errors: nine judges provide roughly the effective information of two independent ones, and aggregation closes only a small fraction of the gap.
arXiv:2607. 05806v1 Announce Type: new Abstract: Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered.
The paper investigates whether stacking multiple defenses around large language models (LLMs) truly compounds security. Using the Adversary Access‑Tier Model (AATM) and a cost‑tiering system, the authors analyze a seven‑layer defense stack and find that failure correlations between layers are consistently positive, meaning the residual attack success is higher than the multiplicative prediction. Despite high coverage and low false refusals, the stack’s performance is largely driven by common architectural causes rather than diverse, independent defenses.
arXiv:2608. 16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost.
The paper argues that traditional semantic similarity fails to capture the true diversity of language models. It introduces a new metric—generative‑process diversity—measured via Normalised Compression Distance on raw outputs, which reveals hidden population structure among 38 models. This metric predicts lower correlated failures across ten benchmark families, independent of semantic similarity or model capability.
The paper introduces a new measure of generative‑process diversity for language models, using Normalised Compression Distance on raw outputs after controlling for permutation effects. Across 38 models, this metric uncovers population structure that semantic similarity misses and predicts lower correlated failures across ten benchmark families, independent of semantic similarity or model capability. The authors argue that higher generative‑process diversity reduces correlated failures in multi‑model systems, offering a practical tool for safety‑relevant applications.
arXiv:2609.21277v1 Announce Type: cross Abstract: How many human judgments does a panel of language models represent? The answer depends on what is matched. We audit categorical judge panels against...
arXiv:2610. 00445v1 Announce Type: new Abstract: Pairwise guide--transcript scores do not enforce conservation of a finite guide-loaded RISC pool when they are interpreted independently as occupancies.
The paper introduces a pluralistic agreement index, Gamma, to quantify how often wrong runs of large language models (LLMs) agree with the majority consensus. By decomposing Gamma into a mechanical component and a preference‑unexplained residual, the authors show that on GPT‑4.1 the mechanical part explains most of the agreement on multiple‑choice benchmarks but only about half on open‑domain tasks, revealing a residual bias that can cause self‑consistency to backfire on hard questions. The study provides a quantitative framework for understanding when majority voting over LLM samples improves or harms accuracy, without proposing new voting methods.
arXiv:2609.39229v1 Announce Type: cross Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary fr...