This paper evaluates the performance of a Large Language Model (LLM) in a high-stakes context by comparing it to human experts and measuring variance and error magnitude.

The paper introduces an LLM-based pipeline that tags learning resources with structured competencies, achieving strong performance while providing traceable evidence and leveraging graph constraints.

This study compares different levels of LLM access in a statistics course, finding that structured, guided use significantly improves students' reasoning skills and independent learning compared to un…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper introduces BenGER, a comprehensive benchmark for evaluating LLMs on German legal reasoning, demonstrating that closed-flagship models perform best and that human-AI co-creation significantly…

The paper introduces Multi-Legal-Bench, a novel cross-jurisdictional benchmark evaluating LLMs on five standardized legal reasoning tasks across six diverse countries, demonstrating that cross-lingual…

This study finds that when users do not specify a jurisdiction, the language used in the prompt strongly biases the LLM's response toward a specific national legal framework (U.S. for English, China f…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

The paper introduces LongJudgeBench, a new benchmark designed to evaluate the reliability of LLM judges specifically for complex, long-form output evaluation, revealing significant instability gaps in…

The paper introduces Synthesis Data Reversion (SDR), a method that infers the data laundering transformation used in LLM training and synthesizes queries to restore the detection signals lost when pro…

This paper systematically analyzes the forensic artifacts left by popular local LLM runners (Ollama, LM Studio, llama.cpp) on Windows and Linux, providing a foundational corpus of evidence for digital…

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

The study found that constraining LLM access, rather than banning it, can preserve students' sense of authorship and encourage more strategic writing behaviors while still providing scaffolding benefi…

This study benchmarks four local LLMs for natural-language-to-SQL querying in biopharma manufacturing, finding that general-purpose code-tuned models like Llama 3.1 8B and Qwen 2.5 Coder 7B outperform…

This paper empirically evaluates LLM-generated reviews for academic papers, finding that while LLM reviews show some alignment with human ones, authors can effectively 'game' the system using iterativ…

This paper investigates the 'faithfulness gap' in LLM agents—the discrepancy between stated reasoning and actual action—by decomposing it into two opposing steps: reasoning-to-conclusion and conclusio…

The paper analyzes GitHub security advisories for LLM-integrated open-source systems, finding that while most vulnerabilities map to existing code-level weaknesses, the architectural risks like Supply…

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

The paper designs and evaluates a triadic LLM-Teacher collaboration system for K-12 writing, finding that strategic labor division between the LLM and teacher effectively improves writing quality but…