The paper introduces NumLeak, a framework demonstrating that top-tier LLMs often exhibit high fidelity recall of specific public numeric benchmarks, suggesting that their apparent skill may be due to…

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper introduces the Data-centric Reasoning Compiler (DCRC), a novel data-driven framework that enhances financial QA systems by compiling user queries and retrieved documents into verifiable, exe…

The paper introduces FinVerBench, a comprehensive benchmark for financial statement verification, concluding that successful verification requires calibrated judgment under realistic observational con…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

The paper introduces a large, consensus-labeled prompt bank that reliably distinguishes between requests for executable malicious code and requests for harmful security knowledge, providing a standard…

The paper demonstrates that using raw source text for fine-tuning LLMs on vulnerability detection causes high false-positive rates by memorizing surface-level syntax, a problem mitigated by using Abst…

The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.

The paper introduces a novel, per-token feature derived from how sampling temperature reshapes the token distribution, demonstrating it is a significantly stronger predictor of LLM creativity than sta…

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…

This study re-evaluates LLM package hallucination rates on a new cohort of frontier models, finding a significant reduction in overall hallucination rates but identifying a persistent, model-agnostic…

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

The paper introduces FormInv, a measurement protocol that reveals significant semantic inconsistencies in existing mathematical reasoning benchmarks, showing that standard accuracy metrics fail to cap…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

MEMENTO proposes a novel framework that treats the open web as a continuous learning signal, enabling agents to acquire task-specific expertise and reusable research strategies in low-data domains wit…

The paper introduces AMNESIA, the first large-scale, open-source benchmark for medical unlearning, demonstrating that current unlearning methods struggle to separate individual patient data from share…

The paper formalizes LLM degradation during long generation as 'cognitive fatigue' and introduces the Fatigue Index (FI), a measurable, model-agnostic diagnostic tool for real-time monitoring.