ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science

• URL: http://arxiv.org/abs/2408.01966v2
• Date: Tue, 27 Aug 2024 20:05:59 GMT
• Title: ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science
• Abstract summary: This research introduces the Multilevel Embedding Association Test (ML-EAT) The ML-EAT addresses issues of ambiguity and difficulty in interpreting the traditional EAT measurement. Using the ML-EAT, this research defines a taxonomy of EAT patterns describing the nine possible outcomes of an embedding association test.
• Score: 18.682235650233743
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This research introduces the Multilevel Embedding Association Test (ML-EAT), a method designed for interpretable and transparent measurement of intrinsic bias in language technologies. The ML-EAT addresses issues of ambiguity and difficulty in interpreting the traditional EAT measurement by quantifying bias at three levels of increasing granularity: the differential association between two target concepts with two attribute concepts; the individual effect size of each target concept with two attribute concepts; and the association between each individual target concept and each individual attribute concept. Using the ML-EAT, this research defines a taxonomy of EAT patterns describing the nine possible outcomes of an embedding association test, each of which is associated with a unique EAT-Map, a novel four-quadrant visualization for interpreting the ML-EAT. Empirical analysis of static and diachronic word embeddings, GPT-2 language models, and a CLIP language-and-image model shows that EAT patterns add otherwise unobservable information about the component biases that make up an EAT; reveal the effects of prompting in zero-shot models; and can also identify situations when cosine similarity is an ineffective metric, rendering an EAT unreliable. Our work contributes a method for rendering bias more observable and interpretable, improving the transparency of computational investigations into human minds and societies.

Related papers

• Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests [0.0]
  We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word Embedding Association Test (WEAT)<n>ZCA whitening transforms the covariance of the embedding space into the identity matrix while minimizing perturbation to the original vectors.<n>We evaluate our approach on ten standard WEAT test suites and seven models spanning three architectural families, yielding 70 model-task combinations.
  arXiv  Detail & Related papers  (2026-08-07T07:42:26Z)
• Modeling semantic association in self-paced reading with language model embeddings [1.647226581907515]
  We use embeddings from LMs to estimate semantic association on a corpus of electroencephalography (EEG) and self-paced reading of natural, Dutch texts.<n>The choice of embedding model can alter the estimated effect of semantic association on both the N400 and self-paced reading times.
  arXiv  Detail & Related papers  (2026-06-05T09:06:22Z)
• UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning [101.62386137855704]
  We present a novel Universal Multimodal Embedding (UniME-V2) model.<n>Our approach first constructs a potential hard negative set through global retrieval.<n>We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs.<n>These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives.
  arXiv  Detail & Related papers  (2025-10-15T13:07:00Z)
• Large Language Models as Neurolinguistic Subjects: Identifying Internal Representations for Form and Meaning [49.60849499134362]
  This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning) Traditional psycholinguistic evaluations often reflect statistical biases that may misrepresent LLMs' true linguistic capabilities. We introduce a neurolinguistic approach, utilizing a novel method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.
  arXiv  Detail & Related papers  (2024-11-12T04:16:44Z)
• Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors [35.37586279472797]
  Concept Vector Activations (CAVs) are learnt using a probe dataset of concept exemplars. We investigate three properties of CAVs: inconsistency across layers, (2) entanglement with other concepts, and (3) spatial dependency. We introduce tools designed to detect the presence of these properties, provide insight into how each property can lead to misleading explanations, and provide recommendations to mitigate their impact.
  arXiv  Detail & Related papers  (2024-04-04T17:46:20Z)
• Compositional Zero-shot Learning via Progressive Language-based Observations [14.85007028612901]
  We propose Progressive Language-based Observations (PLO), which can dynamically determine a better observation order of primitives. PLO adopts pre-trained vision-language models (VLMs) to empower the model with observation capabilities.
  arXiv  Detail & Related papers  (2023-11-23T10:14:23Z)
• Explore Spurious Correlations at the Concept Level in Language Models for Text Classification [28.832684088975622]
  Language models (LMs) have achieved notable success in numerous NLP tasks. They face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations.
  arXiv  Detail & Related papers  (2023-11-15T01:58:54Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Unsupervised discovery of Interpretable Visual Concepts [0.0]
  We propose two methods to explain a model's decision, enhancing global interpretability. One method is inspired by Occlusion and Sensitivity analysis (incorporating causality) The other method uses a novel metric, called Class-aware Order Correlation (CaOC), to globally evaluate the most important image regions.
  arXiv  Detail & Related papers  (2023-08-31T07:53:02Z)
• Translational Concept Embedding for Generalized Compositional Zero-shot Learning [73.60639796305415]
  Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework.
  arXiv  Detail & Related papers  (2021-12-20T21:27:51Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)

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.