Apparent psychological profiles of LLMs are largely measurement artifacts driven by directional response bias rather than actual traits.
Title resolution pending
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4representative citing papers
MAVN adaptively selects and connects virtual nodes in MPNNs via learned dual-perspective preferences, proves it can realize any connectivity pattern, and reports up to 46.5% gains over backbones on nine datasets.
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
The Decision Event Schema (DES) is a unified JSON schema that records governance evidence from four infrastructure layers in a single per-decision event structure with tiered completeness options.
Agentic AI re-identifies 72% of individuals from simulated mobility traces by cross-referencing public web sources without human intervention.
Asteria is a runtime system that enables second-order optimization for LLMs by dynamically distributing optimizer state across GPU, CPU, and NVMe while using asynchronous inverse-root computations and bounded-staleness synchronization.
Pilot study shows agent decision reconstructability varies by vendor SDK regime, with completeness scores from 42.9% to 85.7% and consistent gaps in reasoning traces.
Hard distractors trigger a nonlinear 'First Drop of Ink' performance collapse in long-context LLM reasoning, with most damage from the initial small fraction via disproportionate attention.
Autonomous excavator controller achieves 1.8 cm RMSE in heavy-duty grading across different hydraulic architectures, outperforming commercial solutions by a factor of 2.6 in precision while better utilizing machine pressure.
Dual-Guard embeds complementary watermarks in diffusion image generation to verify provenance and localize tampering with low error rates on a 2400-sample benchmark under reprompting and editing attacks.
Empirical study of eight LLMs finds overuse of popular libraries like NumPy in up to 45% of unnecessary cases and strong default preference for Python even when suboptimal.
KAPPS is a knowledge-based CPPS architecture that uses an ontology-grounded knowledge graph as the unifying data backbone and authoritative write-time state for handling uncertainty in circular manufacturing, demonstrated via anomaly detection and constraint enforcement use cases.
Synthesizes a governance evidence framework revealing a coverage gradient from full auditability in rule engines to structural breaks in agentic AI, with a cascade of uncertainty and four formal propositions.
DNNs plus SHAP/SSHAP applied to 39 European bidding zones identify solar and gas as key price drivers and simulate a single-price EU market.
DEMM defines four executable evidence-sufficiency categories plus a conflicting category for agentic AI decisions and rolls per-property verdicts into a five-level maturity rubric.
A human-in-control LLM architecture translates natural language to OpenSearch DSL queries using hybrid lexical and semantic search in a secure private-cloud setup, shown via prototype on the Enron dataset.
Rule-based annotation generation for ACSL outperforms LLM-based methods in achieving successful formal verification of C programs.
citing papers explorer
-
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact
Apparent psychological profiles of LLMs are largely measurement artifacts driven by directional response bias rather than actual traits.
-
Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Graphs
MAVN adaptively selects and connects virtual nodes in MPNNs via learned dual-perspective preferences, proves it can realize any connectivity pattern, and reports up to 46.5% gains over backbones on nine datasets.
-
RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow
RAG-Reflect achieves F1=0.78 on valid comment-edit prediction using retrieval-augmented reasoning and self-reflection, outperforming baselines and approaching fine-tuned models without retraining.
-
Decision Trace Schema for Governance Evidence in Real-Time Risk Systems
The Decision Event Schema (DES) is a unified JSON schema that records governance evidence from four infrastructure layers in a single per-decision event structure with tiered completeness options.
-
Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy
Agentic AI re-identifies 72% of individuals from simulated mobility traces by cross-referencing public web sources without human intervention.
-
Runtime-Orchestrated Second-Order Optimization for Scalable LLM Training
Asteria is a runtime system that enables second-order optimization for LLMs by dynamically distributing optimizer state across GPU, CPU, and NVMe while using asynchronous inverse-root computations and bounded-staleness synchronization.
-
Property-Level Reconstructability of Agent Decisions: An Anchor-Level Pilot Across Vendor SDK Adapter Regimes
Pilot study shows agent decision reconstructability varies by vendor SDK regime, with completeness scores from 42.9% to 85.7% and consistent gaps in reasoning traces.
-
The First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning
Hard distractors trigger a nonlinear 'First Drop of Ink' performance collapse in long-context LLM reasoning, with most damage from the initial small fraction via disproportionate attention.
-
High Precision Hydraulic Excavator Control for Heavy-Duty Grading
Autonomous excavator controller achieves 1.8 cm RMSE in heavy-duty grading across different hydraulic architectures, outperforming commercial solutions by a factor of 2.6 in precision while better utilizing machine pressure.
-
Dual-Guard: Dual-Channel Latent Watermarking for Provenance and Tamper Localization in Diffusion Images
Dual-Guard embeds complementary watermarks in diffusion image generation to verify provenance and localize tampering with low error rates on a 2400-sample benchmark under reprompting and editing attacks.
-
A Study of LLMs' Preferences for Libraries and Programming Languages
Empirical study of eight LLMs finds overuse of popular libraries like NumPy in up to 45% of unnecessary cases and strong default preference for Python even when suboptimal.
-
KAPPS: A knowledge-based CPPS Architecture for the Circular Factory
KAPPS is a knowledge-based CPPS architecture that uses an ontology-grounded knowledge graph as the unifying data backbone and authoritative write-time state for handling uncertainty in circular manufacturing, demonstrated via anomaly detection and constraint enforcement use cases.
-
Governed Auditable Decisioning Under Uncertainty: Synthesis and Agentic Extension
Synthesizes a governance evidence framework revealing a coverage gradient from full auditability in rule engines to structural breaks in agentic AI, with a cascade of uncertainty and four formal propositions.
-
Analysing drivers and interdependencies in European electricity markets using XAI
DNNs plus SHAP/SSHAP applied to 39 European bidding zones identify solar and gas as key price drivers and simulate a single-price EU market.
-
Decision Evidence Maturity Model for Agentic AI: A Property-Level Method Specification
DEMM defines four executable evidence-sufficiency categories plus a conflicting category for agentic AI decisions and rolls per-property verdicts into a five-level maturity rubric.
-
A Cloud-Native Architecture for Human-in-Control LLM-Assisted OpenSearch in Investigative Settings
A human-in-control LLM architecture translates natural language to OpenSearch DSL queries using hybrid lexical and semantic search in a secure private-cloud setup, shown via prototype on the Enron dataset.
-
Evaluating LLM-Generated ACSL Annotations for Formal Verification
Rule-based annotation generation for ACSL outperforms LLM-based methods in achieving successful formal verification of C programs.
- SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents