EigenBench: A Comparative Behavioral Measure of Value Alignment

• URL: http://arxiv.org/abs/2509.01938v3
• Date: Fri, 26 Sep 2025 01:58:19 GMT
• Title: EigenBench: A Comparative Behavioral Measure of Value Alignment
• Authors: Jonathn Chang, Leonhard Piff, Suvadip Sana, Jasmine X. Li, Lionel Levine,
• Abstract summary: EigenBench is a black-box method for benchmarking language models' values.<n>It is designed to quantify subjective traits for which reasonable judges may disagree on the correct label.<n>It can recover model rankings on the GPQA benchmark without access to objective labels.
• Score: 0.28707625120094377
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligning AI with human values is a pressing unsolved problem. To address the lack of quantitative metrics for value alignment, we propose EigenBench: a black-box method for comparatively benchmarking language models' values. Given an ensemble of models, a constitution describing a value system, and a dataset of scenarios, our method returns a vector of scores quantifying each model's alignment to the given constitution. To produce these scores, each model judges the outputs of other models across many scenarios, and these judgments are aggregated with EigenTrust (Kamvar et al., 2003), yielding scores that reflect a weighted consensus judgment of the whole ensemble. EigenBench uses no ground truth labels, as it is designed to quantify subjective traits for which reasonable judges may disagree on the correct label. Hence, to validate our method, we collect human judgments on the same ensemble of models and show that EigenBench's judgments align closely with those of human evaluators. We further demonstrate that EigenBench can recover model rankings on the GPQA benchmark without access to objective labels, supporting its viability as a framework for evaluating subjective values for which no ground truths exist.

Related papers

• IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation [85.56193980646981]
  We propose IF-RewardBench, a comprehensive meta-evaluation benchmark for instruction-following.<n>For each instruction, we construct a preference graph containing all pairwise preferences among multiple responses.<n>Experiments on IF-RewardBench reveal significant deficiencies in current judge models.
  arXiv  Detail & Related papers  (2026-03-05T02:21:17Z)
• Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models [55.94503936470247]
  Large-scale AI evaluation increasingly relies on aggregating binary judgments from $K$ annotators, including judges.<n>Most classical methods assume annotators are conditionally independent given the true label $Yin0,1$, an assumption often violated by LLM judges.<n>We study label aggregation through a hierarchy of dependence-aware models based on Ising graphical models and latent factors.
  arXiv  Detail & Related papers  (2026-01-29T21:26:50Z)
• VAL-Bench: Measuring Value Alignment in Language Models [10.745372809345412]
  Large language models (LLMs) are increasingly used for tasks where outputs shape human decisions.<n>Existing benchmarks mostly track refusals or predefined safety violations but do not reveal whether a model upholds a coherent value system.<n>We introduce the Value ALignment Benchmark (VAL-Bench), which evaluates whether models maintain a stable value stance across paired that frame opposing sides of public debates.
  arXiv  Detail & Related papers  (2025-10-06T23:55:48Z)
• Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items [2.9357382494347264]
  Existing benchmarks rely on human or machine annotations that are vulnerable to value-related biases.<n>We propose the Value Portrait benchmark, which consists of items that capture real-life user-LLM interactions.<n>This psychometrically validated approach ensures that items strongly correlated with specific values serve as reliable items for assessing those values.
  arXiv  Detail & Related papers  (2025-05-02T05:26:50Z)
• Where is this coming from? Making groundedness count in the evaluation of Document VQA models [12.951716701565019]
  We argue that common evaluation metrics do not account for the semantic and multimodal groundedness of a model's outputs.<n>We propose a new evaluation methodology that accounts for the groundedness of predictions.<n>Our proposed methodology is parameterized in such a way that users can configure the score according to their preferences.
  arXiv  Detail & Related papers  (2025-03-24T20:14:46Z)
• How to Select Datapoints for Efficient Human Evaluation of NLG Models? [57.60407340254572]
  We develop and analyze a suite of selectors to get the most informative datapoints for human evaluation.<n>We show that selectors based on variance in automated metric scores, diversity in model outputs, or Item Response Theory outperform random selection.<n>In particular, we introduce source-based estimators, which predict item usefulness for human evaluation just based on the source texts.
  arXiv  Detail & Related papers  (2025-01-30T10:33:26Z)
• How Many Ratings per Item are Necessary for Reliable Significance Testing? [7.777020199676859]
  Most approaches to machine learning evaluation assume that machine and human responses are repeatable enough to be measured against data with unitary authoritative, "gold standard" responses.<n>We introduce methods for determining whether an (existing or planned) evaluation dataset has enough responses per item to reliably compare the performance of one model to another.
  arXiv  Detail & Related papers  (2024-12-04T02:31:28Z)
• The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models [94.31327813151208]
  BiGGen Bench is a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks.<n>A key feature of the BiGGen Bench is its use of instance-specific evaluation criteria, closely mirroring the nuanced discernment of human evaluation.
  arXiv  Detail & Related papers  (2024-06-09T12:30:30Z)
• A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions [60.06461883533697]
  We first identify a set of fidelity criteria that reliable benchmarks for attribution methods are expected to fulfill.<n>We then introduce a Backdoor-based eXplainable AI benchmark (BackX) that adheres to the desired fidelity criteria.<n>Our analysis also offers insights into defending against neural Trojans by utilizing the attributions.
  arXiv  Detail & Related papers  (2024-05-02T13:48:37Z)
• Evaluating the Fairness of Discriminative Foundation Models in Computer Vision [51.176061115977774]
  We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP) We then systematically evaluate existing methods for mitigating bias in these models with respect to our taxonomy. Specifically, we evaluate OpenAI's CLIP and OpenCLIP models for key applications, such as zero-shot classification, image retrieval and image captioning.
  arXiv  Detail & Related papers  (2023-10-18T10:32:39Z)
• Anchor Points: Benchmarking Models with Much Fewer Examples [88.02417913161356]
  In six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the entire dataset. Just several anchor points can be used to estimate model per-class predictions on all other points in a dataset with low mean absolute error.
  arXiv  Detail & Related papers  (2023-09-14T17:45:51Z)
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets [69.91340332545094]
  We introduce FLASK, a fine-grained evaluation protocol for both human-based and model-based evaluation. We experimentally observe that the fine-graininess of evaluation is crucial for attaining a holistic view of model performance.
  arXiv  Detail & Related papers  (2023-07-20T14:56:35Z)
• Efficient Shapley Values Estimation by Amortization for Text Classification [66.7725354593271]
  We develop an amortized model that directly predicts each input feature's Shapley Value without additional model evaluations. Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup.
  arXiv  Detail & Related papers  (2023-05-31T16:19:13Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [49.15931834209624]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world.<n>We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.<n>By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Evaluating Representations with Readout Model Switching [19.907607374144167]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• Utilizing supervised models to infer consensus labels and their quality from data with multiple annotators [16.79939549201032]
  Real-world data for classification is often labeled by multiple annotators. We introduce CROWDLAB, a straightforward approach to estimate such data. Our proposed method provides superior estimates for (1)- (3) than many alternative algorithms.
  arXiv  Detail & Related papers  (2022-10-13T07:54:07Z)
• Rater Equivalence: Evaluating Classifiers in Human Judgment Settings [11.529701822081394]
  We introduce a framework for evaluating automated classifiers based solely on human judgments.<n>Our framework uses human-generated labels both to construct benchmark panels and to evaluate performance.<n>Using case studies and formal analysis, we demonstrate how this framework can inform the evaluation and deployment of AI systems.
  arXiv  Detail & Related papers  (2021-06-02T16:07:32Z)
• Characterizing Fairness Over the Set of Good Models Under Selective Labels [69.64662540443162]
  We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance. We provide tractable algorithms to compute the range of attainable group-level predictive disparities. We extend our framework to address the empirically relevant challenge of selectively labelled data.
  arXiv  Detail & Related papers  (2021-01-02T02:11:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.