Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumulate hidden structural contradictions, safety risks, and systemic human annotation errors. Standard dataset auditing methods, such as semantic deduplication or LLM-as-a-judge, struggle to capture the actual predictive impact of individual records and often miss deep functional rule clashes. To address this, we introduce a scalable, inference-only data valuation pipeline that approximates the Shapley value without iterative model retraining. By mapping semantic k-NN neighborhoods into a directed graph, our framework evaluates data utility directly through a reference LLM's probability distribution using zero-shot and one-shot conditional log-likelihood shifts. Our pipeline then translates these predictive influence scores into localized advantage metrics to isolate gradient-conflicting records. We demonstrate the pipeline's efficacy in sanitizing two heavily vetted alignment datasets. First, applying our pipeline to the HelpSteer2 dataset reduced the manual audit search space by 99.1%, successfully uncovering falsely-labeled records across diverse failure modes. Second, applying our automated audit strategy to Anthropic's HH-RLHF training and evaluation splits identified thousands of hidden safety and factual preference inversions. Crucially, by extending this audit to the evaluation split, we expose severe vulnerabilities in current benchmark integrity: highly capable models frequently predict the safer or more helpful response, only to be penalized by objectively flawed human ground-truth labels. Overall, our work provides a mathematically grounded, highly efficient diagnostic tool to uncover human label failures, sanitize evaluation benchmarks, and ensure the integrity of LLM alignment data.

Critical Features Tracking on Triangulated Irregular Networks by a Scale-Space Method

The scale-space method is a well-established framework that constructs a hierarchical representation of an input signal and facilitates coarse-to-fine visual reasoning. Considering the terrain elevation function as the input signal, the scale-space method can identify and track significant topographic features across different scales. The number of scales a feature persists, called its life span, indicates the importance of that feature. In this way, important topographic features of a landscape can be selected, which are useful for many applications, including cartography, nautical charting, and land-use planning. The scale-space methods developed for terrain data use gridded Digital Elevation Models (DEMs) to represent the terrain. However, gridded DEMs lack the flexibility to adapt to the irregular distribution of input data and the varied topological complexity of different regions. Instead, Triangulated Irregular Networks (TINs) can be directly generated from irregularly distributed point clouds and accurately preserve important features. In this work, we introduce a novel scale-space analysis pipeline for TINs, addressing the multiple challenges in extending grid-based scale-space methods to TINs. Our pipeline can efficiently identify and track topologically important features on TINs. Moreover, it is capable of analyzing terrains with irregular boundaries, which poses challenges for grid-based methods. Comprehensive experiments show that, compared to grid-based methods, our TIN-based pipeline is more efficient, accurate, and has better resolution robustness.