Lune

EMNLP Findings2025

Extracting Conceptual Spaces from LLMs Using Prototype Embeddings

Nitesh Kumar, Usashi Chatterjee, Steven Schockaert

Abstract

Conceptual spaces represent entities and concepts using cognitively meaningful dimensions, typically referring to perceptual features. Such representations are widely used in cognitive science and have the potential to serve as a cornerstone for explainable AI. Unfortunately, they have proven notoriously difficult to learn, although recent LLMs appear to capture the required perceptual features to a remarkable extent. Nonetheless, practical methods for extracting the corresponding conceptual spaces are currently still lacking. While various methods exist for extracting embeddings from LLMs, extracting conceptual spaces also requires us to encode the underlying features. In this paper, we propose a strategy in which features (e.g. sweetness) are encoded by embedding the description of a corresponding prototype (e.g. a very sweet food). To improve this strategy, we fine-tune the LLM to align the prototype embeddings with the corresponding conceptual space dimensions. Our empirical analysis finds this approach to be highly effective.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on16

  1. SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 citations
  2. The Linear Representation Hypothesis and the Geometry of Large Language ModelsKiho Park, Yo Joong Choe, Victor VeitchICML 2024 · 461 citations
  3. Mapping Language Models to Grounded Conceptual SpacesRoma Patel, Ellie PavlickICLR 2022 · 197 citations
  4. Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut et al.ACL 2020 · 168 citations
  5. Interpreting Pretrained Contextualized Representations via Reductions to Static EmbeddingsRishi Bommasani, Kelly Davis, Claire CardieACL 2020 · 137 citations

Related papers

  1. Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning StrategiesNitesh Kumar, Usashi Chatterjee, Steven SchockaertACL Findings 2024 · 1 citation
  2. Interpreting Embedding Spaces by ConceptualizationAdi Simhi, Shaul MarkovitchEMNLP 2023 · 6 citations
  3. VibeSpace: Automatic Generation of Data and Vector Embeddings for Arbitrary Domains and Cross-domain Mappings using LLMsKipp Freud, Daniel E. Collins, Delmiro D. Sampaio Neto, Grant StevensACM MM 2025
  4. Towards Concept-Aware Large Language ModelsChen Shani, Jilles Vreeken, Dafna ShahafEMNLP Findings 2023
  5. Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept DiscoveryYifan Sun, Danding Wang, Qiang Sheng, Juan Cao et al.ACL Findings 2025
Dusk over the sea between two cliffs drawn in fine vertical lines