The paper introduces Prosecution Decision Prediction (PDP), a new legal AI task that assesses prosecutorial review decisions, showing that current state-of-the-art LLMs perform significantly worse on…

This paper evaluates the reliability of using Large Language Models (LLMs) as automated judges to assess the quality of other LLMs, finding a high correlation with human judgment when suitable prompts…

The paper introduces the DECK taxonomy, a novel framework that classifies LLM hallucinations not by their content error, but by their detectability signature based on inter-sample consistency and toke…

The paper proposes a novel, practical upper bound to estimate the worst-case performance of medical prediction models on the target population, even when the selection bias mechanism and target data a…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…

This paper argues that reporting only the best-case attack success rate for jailbreaks is insufficient, proposing new distributional metrics (VSM and UC) to better characterize the true threat posed b…

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

The paper introduces a framework using the 'behavioral geometry' of model populations to efficiently predict jailbreak susceptibility and transfer defenses, achieving high accuracy with significantly…

The paper investigates how different methods of jailbreaking large language models (SFT, RLVR, and abliteration) lead to vastly different behavioral and mechanistic failures, even when all methods ach…

The paper proposes a Bayesian meta-learner to accurately predict the distribution of Alzheimer's disease progression scores for individuals, outperforming existing methods, especially for long-term pr…

The paper proposes a framework to model moral reasoning as an ethical distribution (ethical pluralism) rather than a single binary judgment, achieving high classification accuracy by integrating norma…

The paper proposes a finite-calibration regime map to determine the optimal calibration method (low-dimensional stackers vs. joint tables) for LLM judge panels given limited human labeling budgets, sh…

The paper introduces a comprehensive framework, Realtime Risk Studio, that operationalizes qualitative risk models (Bowtie diagrams) into formal, probabilistic, and intervention-ready runtime models u…

The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…

The paper evaluates the inconsistency of using LLMs as automated judges for multi-dimensional safety evaluations, finding that LLMs are unreliable for nuanced safety issues like financial advice but m…

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime…

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.