AIBullisharXiv – CS AI · Jun 47/10
🧠Researchers propose an ontology-grounded framework for pre-deployment verification of enterprise AI agents, combining formalized operational envelopes with automated regulatory scenario generation and trust certification. A controlled pilot across fintech, banking, insurance, and healthcare found ontology-based testing achieved 48.3% regulatory coverage versus 33.1% for persona-based baselines, establishing a new standard for AI safety assurance in regulated industries.
🧠 Claude🧠 Sonnet
AIBullisharXiv – CS AI · Jun 47/10
🧠PerceptTwin is an automated pipeline that generates interactive 3D simulations from robot perception data, enabling LLM-based planners to validate and refine strategies before hardware execution. The system improves plan success rates by approximately 39% and enhances safety through semantic scene reconstruction and LLM verification mechanisms.
🧠 GPT-5
AINeutralarXiv – CS AI · Jun 27/10
🧠Researchers introduce PAVE, a diagnostic framework for evaluating how large language models arbitrate between their parametric knowledge and retrieved evidence in RAG-based fact-checking systems. Testing across seven LLMs reveals inconsistent and model-dependent behavior when prior knowledge conflicts with retrieved context, prompting the development of a lightweight test-time correction method to improve factual reliability.
AIBullisharXiv – CS AI · Jun 27/10
🧠Researchers introduce Expected Value Alignment (EVA), a novel reward-modeling technique that enables Large Language Models to provide continuous numerical scores while maintaining human-readable text output for formal mathematics verification in Lean 4. The method bridges a critical gap between discrete generative outputs and continuous value assessment needed for reinforcement learning in theorem proving systems.
AIBullisharXiv – CS AI · May 277/10
🧠Researchers present a hybrid neuro-symbolic architecture that combines formal logic with neural semantic analysis to verify LLM outputs in high-stakes domains like healthcare. The system achieves over 83% hallucination detection rates for structured data and 72% for semantic fabrications while reducing report creation time by 30%, demonstrating practical safeguards for deploying LLMs in data-sensitive applications.
AIBullisharXiv – CS AI · Apr 207/10
🧠Researchers introduce AgentV-RL, an agentic verifier framework that enhances reward modeling for large language models by combining bidirectional reasoning agents with tool-use capabilities. The system addresses critical limitations in LLM verification by enabling forward and backward tracing of solutions, achieving 25.2% performance gains over existing methods and positioning agentic reward modeling as a promising new paradigm.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers propose a two-stage LLM framework that uses one model to translate XAI technical outputs into natural language and a second model to verify accuracy, faithfulness, and completeness before delivering explanations to users. The framework includes iterative refinement mechanisms and demonstrates improved reliability across multiple XAI techniques and LLM families.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers introduce αNeSy-CTM, a hybrid neurosymbolic framework combining Large Language Models with logical verification to automate clinical trial matching. The system achieves 30% relative improvement over zero-shot baselines by leveraging LLM language capabilities alongside formal symbolic reasoning to handle incomplete patient records and complex eligibility criteria.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers present a human-in-the-loop framework combining fine-tuned small language models with knowledge graphs to automatically detect and repair semantic errors in SysML v2 models that bypass traditional compiler validation. The approach achieves over 91% repair accuracy using domain-specific training data and generates practical repair suggestions for engineer review.
AIBullisharXiv – CS AI · Jun 196/10
🧠Researchers developed a dual-agent AI framework that translates natural-language biological protocols into executable commands for robotic laboratory platforms, bridging the semantic gap between human-written experiments and automated systems. The system uses a Parser Agent to structure protocols and a Validation Agent to verify accuracy, with successful demonstration on real microplate-based experiments.
AINeutralarXiv – CS AI · Jun 106/10
🧠Researchers developed a step-level verification framework that improves Large Language Models' ability to evaluate complex mathematical proofs by maintaining detailed context for each deduction and constraining theorem sources, rather than relying on global evaluation. Testing on research-level proofs revealed that unconstrained approaches fail to catch subtle logical errors, while the new method reveals that remaining verification failures stem from implicit domain conventions rather than hallucinations.
AIBullisharXiv – CS AI · Jun 106/10
🧠Researchers propose SAFE, an LLM-as-verifier framework that improves multi-hop question answering by validating reasoning steps against evidence during generation rather than only checking final answers. The approach uses Knowledge Graph triples to decompose reasoning into verifiable units and achieves 8.8 percentage point accuracy improvements across three benchmarks.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers present MedSci Skills, an open-source toolkit that pairs LLM-assisted clinical manuscript generation with deterministic verification gates to detect fabricated citations, numerical errors, and missing reporting guidelines. The system demonstrates 100% detection of seeded defects versus 41% for generic LLM reviewers, providing an auditable trail for biomedical publishing.
AINeutralarXiv – CS AI · Jun 85/10
🧠Researchers have developed Miffie, an AI-powered framework that automates database normalization using large language models with a dual-model self-refinement architecture. The system combines schema generation and verification modules to eliminate data anomalies while maintaining high accuracy, reducing manual effort by data engineers.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers present DeepSciVerify, an LLM-based system that verifies scientific claims against cited evidence by combining abstract-level analysis with selective full-text passage retrieval. The two-stage pipeline achieves 86.7% accuracy on benchmarks while reducing computational overhead by avoiding unnecessary full-text analysis in 67% of cases, addressing a critical reliability issue in AI-generated scientific content.
AINeutralarXiv – CS AI · May 286/10
🧠Researchers introduce LegalGraphRAG, a framework that combines hierarchical graph structures with multi-agent verification to improve legal reasoning in AI systems. The approach addresses critical limitations in applying retrieval-augmented generation to legal domains by organizing heterogeneous legal knowledge at multiple abstraction levels and implementing transparent, audited reasoning processes.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers introduce EHR-ReasonCon, a benchmark dataset and EHR-Inspector, an LLM-based framework designed to verify consistency between unstructured clinical notes and structured data in Electronic Health Records. The work addresses a critical gap in healthcare data quality by moving beyond simple value matching to capture clinical reasoning, temporal relationships, and event interpretations that reflect real-world documentation practices.
AIBullisharXiv – CS AI · Apr 206/10
🧠Researchers demonstrate that LLMs can be used as lossless encoders and decoders for invertible problems in hardware design, significantly reducing hallucinations and omissions. By generating HDL code from Logic Condition Tables and reconstructing the original tables to verify accuracy, the approach improves developer productivity and catches both AI-generated errors and design specification flaws.
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers analyzed how LLM verifiers assess solution correctness in test-time scaling scenarios, revealing that verification effectiveness varies significantly with problem difficulty, generator strength, and verifier capability. The study demonstrates that weak generators can nearly match stronger ones post-verification and that verifier scaling alone cannot solve fundamental verification challenges.
🧠 GPT-4
