mlsanityData to 7 Oct 2026

Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer

arXiv 2608.01585 ↗First posted 3 Aug 2026cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Language model benchmarking is a difficult task. Outcome reasoning alone does not test the model's conceptualization of language and popular open-source benchmarks are quickly saturated or ingested as training data. It is important to test the model's output, but augmenting these tests by characterizing semantic structure gives more insight to how models relate abstract concepts. However, the high dimensional embedding spaces are not easy to interpret. This work demonstrates how topological methods can be used to rigorously compare these spaces to low dimensional and interpretable baselines like ontologies and curated knowledge graphs. These multi-modal alignment tests make it possible to track model adaptations and test phrase understanding across multiple languages.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 53 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

37 of 53 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  8. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  9. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  10. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  11. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,359
  12. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
25 more
  1. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  2. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  3. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  5. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  6. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  7. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 738
  8. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 673
  9. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  10. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 478
  11. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  12. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 417
  13. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  14. 2024Alignment faking in large language modelscited by 316
  15. 2023Emergent Linear Representations in World Models of Self-Supervised Sequence Modelscited by 313
  16. 2023Language Models Represent Space and Timecited by 306
  17. 2023MADLAD-400: A Multilingual And Document-Level Large Audited Datasetcited by 180
  18. 2024The Geometry of Categorical and Hierarchical Concepts in Large Language Modelscited by 151
  19. 2025BIG-Bench Extra Hardcited by 123
  20. 2025Demonstrating specification gaming in reasoning modelscited by 48
  21. 2013Stochastic Convergence of Persistence Landscapes and Silhouettescited by 43
  22. 2026TranslateGemma Technical Reportcited by 7
  23. 2022Comparing multiple latent space embeddings using topological analysiscited by 4
  24. 2026ARC Prize 2025: Technical Reportcited by 4
  25. 2026Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Atlas-Alignment: Making Interpretability Transferable Across Language Models
  2. 2026Semantic Invariance in Agentic AI
  3. 2024Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model Generalization
  4. 2025Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
  5. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
  6. 2026Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning
  7. 2022Unpacking Large Language Models with Conceptual Consistency
  8. 2026LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations