Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors

• URL: http://arxiv.org/abs/2601.07995v1
• Date: Mon, 12 Jan 2026 20:54:42 GMT
• Title: Is Sentiment Banana-Shaped? Exploring the Geometry and Portability of Sentiment Concept Vectors
• Authors: Laurits Lyngbaek, Pascale Feldkamp, Yuri Bizzoni, Kristoffer L. Nielbo, Kenneth Enevoldsen,
• Abstract summary: Concept Vector Projections (CVP) produce continuous, multilingual scores that align closely with human judgments.<n>We evaluate CVP across genres, historical periods, languages, and affective dimensions.<n>Our findings suggest that while CVP is a portable approach that effectively captures generalizable patterns, its linearity assumption is approximate.
• Score: 1.665869541468341
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Use cases of sentiment analysis in the humanities often require contextualized, continuous scores. Concept Vector Projections (CVP) offer a recent solution: by modeling sentiment as a direction in embedding space, they produce continuous, multilingual scores that align closely with human judgments. Yet the method's portability across domains and underlying assumptions remain underexplored. We evaluate CVP across genres, historical periods, languages, and affective dimensions, finding that concept vectors trained on one corpus transfer well to others with minimal performance loss. To understand the patterns of generalization, we further examine the linearity assumption underlying CVP. Our findings suggest that while CVP is a portable approach that effectively captures generalizable patterns, its linearity assumption is approximate, pointing to potential for further development.

Related papers

• A Geometric Unification of Concept Learning with Concept Cones [58.70836885177496]
  Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs) and Sparse Autoencoders (SAEs)<n>We show that both paradigms instantiate the same geometric structure.<n>CBMs provide human-defined reference geometries, while SAEs can be evaluated by how well their learned cones approximate or contain those of CBMs.
  arXiv  Detail & Related papers  (2025-12-08T09:51:46Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction [14.396966854171273]
  We consider the problem of single-source domain generalization.<n>Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training.<n>We propose an approach that compels models to leverage such local concepts during prediction.
  arXiv  Detail & Related papers  (2024-11-25T08:46:37Z)
• Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces [1.0923877073891446]
  Insights into the learned latent representations are imperative for verifying deep neural networks (DNNs) in computer vision tasks.<n>We propose a novel local concept analysis framework to allow exploration of learned concept distributions.<n>Despite its context sensitivity, our method's concept segmentation performance is competitive to global baselines.
  arXiv  Detail & Related papers  (2023-11-24T12:22:00Z)
• Identifying Linear Relational Concepts in Large Language Models [16.917379272022064]
  Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations. We present a technique called linear relational concepts (LRC) for finding concept directions corresponding to human-interpretable concepts.
  arXiv  Detail & Related papers  (2023-11-15T14:01:41Z)
• A Geometric Notion of Causal Probing [85.49839090913515]
  The linear subspace hypothesis states that, in a language model's representation space, all information about a concept such as verbal number is encoded in a linear subspace.<n>We give a set of intrinsic criteria which characterize an ideal linear concept subspace.<n>We find that, for at least one concept across two languages models, the concept subspace can be used to manipulate the concept value of the generated word with precision.
  arXiv  Detail & Related papers  (2023-07-27T17:57:57Z)
• Uncovering Unique Concept Vectors through Latent Space Decomposition [0.0]
  Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates. We propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. Our experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand.
  arXiv  Detail & Related papers  (2023-07-13T17:21:54Z)
• On convex decision regions in deep network representations [1.06378109904813]
  We investigate the notion of convexity of concept regions in machine-learned latent spaces. We show that convexity is robust to basic re-parametrization. We find that approximate convexity is pervasive in neural representations in multiple application domains.
  arXiv  Detail & Related papers  (2023-05-26T10:33:03Z)
• Towards a Deeper Understanding of Concept Bottleneck Models Through End-to-End Explanation [2.9740255333669454]
  Concept Bottleneck Models (CBMs) first map raw input(s) to a vector of human-defined concepts, before using this vector to predict a final classification. In doing so, this would support human interpretation when generating explanations of the model's outputs to visualise input features corresponding to concepts.
  arXiv  Detail & Related papers  (2023-02-07T16:43:43Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)

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.