Research map / Label-efficient and robust learning / Recognition and long-tail
Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space
Felipe Diego Toro-Hernández, Jesuino Vieira Filho, Rodrigo M. Cabral-Carvalho
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use cumulative instead of non-cumulative embeddings (long trajectories) (ablation) | OpenAI text-embedding-3-large · Neurodegenerative dataset | significant pairwise differences: 4 -> 10 | Improved |
| use cumulative instead of non-cumulative embeddings (ablation) | OpenAI text-embedding-3-large · Swear Fluency dataset | mean Cohen's d: 0.64 -> 0.59 (pairs 46 -> 46) | Mixed |
| use cumulative instead of non-cumulative embeddings (short trajectories) (ablation) | OpenAI text-embedding-3-large · Italian dataset | significant pairwise differences: 81 -> 63 | Hurt |
| use cumulative instead of non-cumulative embeddings (short trajectories) (ablation) | OpenAI text-embedding-3-large · German dataset | significant pairwise differences: 111 -> 80 | Hurt |
| swap embedding model (OpenAI, Google, Qwen3) (ablation) | trajectory metrics · all four datasets | metric correlation across models | No clear effect |
| apply ZCA whitening to embeddings (ablation) | OpenAI text-embedding-3-large · Neurodegenerative and Swear Fluency | trajectory metrics | No clear effect |
Closest papers by meaning
- Meaning Representations from Trajectories in Autoregressive Models (ICLR 2024 · similarity 0.86)
- The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities (ICLR 2025 · similarity 0.85)
- The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans (NeurIPS 2026 · similarity 0.85)
- ICLR: In-Context Learning of Representations (ICLR 2025 · similarity 0.85)
- The Geometry of Categorical and Hierarchical Concepts in Large Language Models (ICLR 2025 · similarity 0.85)
- Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
