Author name cluster

Xinhe Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

NeurIPS Conference 2025 Conference Paper

Bridging Human and LLM Judgments: Understanding and Narrowing the Gap

Felipe Maia Polo
Xinhe Wang
Mikhail Yurochkin
Gongjun Xu
Moulinath Banerjee
Yuekai Sun

Large language models are increasingly used as judges (LLM-as-a-judge) to evaluate model outputs at scale, but their assessments often diverge systematically from human judgments. We present Bridge, a unified statistical framework that explicitly bridges human and LLM evaluations under both absolute scoring and pairwise comparison paradigms. Bridge posits a latent human preference score for each prompt-response pair and models LLM deviations as linear transformations of covariates that capture sources of discrepancies. This offers a simple and principled framework for refining LLM ratings and characterizing systematic discrepancies between humans and LLMs. We provide an efficient fitting algorithm with asymptotic guarantees for statistical inference. Using six LLM judges and two benchmarks (BigGen Bench and Chatbot Arena), Bridge achieves higher agreement with human ratings (accuracy, calibration, and KL divergence) and exposes systematic human-LLM gaps.

PDF Details

NeurIPS Conference 2024 Conference Paper

$\texttt{dattri}$: A Library for Efficient Data Attribution

Junwei Deng
Ting-Wei Li
Shiyuan Zhang
Shixuan Liu
Yijun Pan
Hao Huang
Xinhe Wang
Pingbang Hu

Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI models, data attribution has found broad applications in improving AI performance and safety. However, despite a surge of new data attribution methods being developed recently, there lacks a comprehensive library that facilitates the development, benchmarking, and deployment of different data attribution methods. In this work, we introduce $\texttt{dattri}$, an open-source data attribution library that addresses the above needs. Specifically, $\texttt{dattri}$ highlights three novel design features. Firstly, $\texttt{dattri}$ proposes a unified and easy-to-use API, allowing users to integrate different data attribution methods into their PyTorch-based machine learning pipeline with a few lines of code changed. Secondly, $\texttt{dattri}$ modularizes low-level utility functions that are commonly used in data attribution methods, such as Hessian-vector product, inverse-Hessian-vector product or random projection, making it easier for researchers to develop new data attribution methods. Thirdly, $\texttt{dattri}$ provides a comprehensive benchmark framework with pre-trained models and ground truth annotations for a variety of benchmark settings, including generative AI settings. We have implemented a variety of state-of-the-art efficient data attribution methods that can be applied to large-scale neural network models, and will continuously update the library in the future. Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods. The source code of $\texttt{dattri}$ is available at https: //github. com/TRAIS-Lab/dattri.

PDF Details DOI

YNIMG Journal 2010 Journal Article

Context-dependent perturbation of neural systems in transgenic mice expressing a cytosolic prion protein

Henryk Faas
Walker S Jackson
Andrew W. Borkowski
Xinhe Wang
Jiyan Ma
Susan Lindquist
Alan Jasanoff

We analyzed the relationship between pathogenic protein expression and perturbations to brain anatomy and physiology in a genetic model of prion disease. In this model, the mouse line 1D4, neuropathology is promoted by accumulation of a cytosolic form of the prion protein (cyPrP). CyPrP distribution was determined and compared with anatomical magnetic resonance imaging (MRI) data, a form of functional MRI based on manganese labeling, and immediate early gene mapping with an antibody to c-Fos. Significant discrepancies between 1D4 and control mice became apparent well in advance of overt behavioral pathology in the mutant mice. Alterations to brain structure and function in the mutants varied among brain regions, however, and differed strikingly even among regions with the highest levels of cyPrP expression. In the cerebellum, gross neurodegeneration was accompanied by increased Mn2+-enhanced MRI signal, raising the possibility that compensatory mechanisms act to preserve cerebellar function in the face of massive atrophy. In the hippocampus of 1D4 mice, no significant structural alterations were observed, but both Mn2+-enhanced MRI and c-Fos data indicated perturbations to neurophysiology. In the neocortex, there were no clear neural activity differences between 1D4 and control animals, but mutant mice showed significant reduction in cortical thickness. Our finding that distinct combinations of anatomical and functional abnormalities accompanied cyPrP overexpression in different parts of the brain indicates the importance of context in conditioning effects of protein pathogens, and exemplifies the notion that neurodegenerative phenotypes extend beyond cell death and the immediate consequences of atrophy for particular neural systems.

Details DOI