TRACE compiles user corrections into runtime enforcement rules for coding agents, cutting preference violations from 100% to 37.6% in-distribution and 2% out-of-distribution on ClawArena tasks while matching memory baselines on task success.
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
VSM modulates the score Jacobian using variance guidance to reduce hallucinations in diffusion models by up to 25% on synthetic and real datasets while preserving fidelity and diversity.
CIE-Scorer detects unfaithful CoT by tracing compact sentence-level circuits, building internal-external reasoning graphs, and scoring their discrepancy with Fused Gromov-Wasserstein distance, reporting SOTA results on FaithCoT-Bench with reduced circuit cost.
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
The paper proposes a paradigm of provable probabilistic safety to enable scalable, safe deployment of embodied AI in critical applications.
citing papers explorer
-
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
TRACE compiles user corrections into runtime enforcement rules for coding agents, cutting preference violations from 100% to 37.6% in-distribution and 2% out-of-distribution on ClawArena tasks while matching memory baselines on task success.
-
Score-Control for Hallucination Reduction in Diffusion Models
VSM modulates the score Jacobian using variance guidance to reduce hallucinations in diffusion models by up to 25% on synthetic and real datasets while preserving fidelity and diversity.
-
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
CIE-Scorer detects unfaithful CoT by tracing compact sentence-level circuits, building internal-external reasoning graphs, and scoring their discrepancy with Fused Gromov-Wasserstein distance, reporting SOTA results on FaithCoT-Bench with reduced circuit cost.
-
ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense
ARENA creates anonymized SOC telemetry artifacts that reveal a measurable privacy-utility boundary when used both as training material for MITRE-mapped challenges and as a substrate to detect non-compliant LLM defender actions.
-
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
-
Emergent Social Intelligence Risks in Generative Multi-Agent Systems
Generative multi-agent systems exhibit emergent collusion and conformity behaviors that cannot be prevented by existing agent-level safeguards.
-
Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging
SFM improves generalization under distribution shift for scientific imaging tasks while AVUQ supplies sample-efficient epistemic and aleatoric uncertainty estimates plus anomaly scores.
-
Towards provable probabilistic safety for scalable embodied AI systems
The paper proposes a paradigm of provable probabilistic safety to enable scalable, safe deployment of embodied AI in critical applications.