mlsanityData to 14 Oct 2026

Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments

arXiv 2504.07965 ↗First posted 10 Apr 2025cs.LG cs.CLcited by 1

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a representational level, allowing investigations of how these levels interact. We evaluate 32 publicly available language models for their representational and behavioral alignment with human similarity judgments on a word triplet task. This provides a novel evaluation setting to probe semantic associations in language beyond common pairwise comparisons. We find that (1) even the representations of small language models can achieve human-level alignment, (2) instruction-tuned model variants can exhibit substantially increased agreement, (3) the pattern of alignment across layers is highly model dependent, and (4) alignment based on models' behavioral responses is highly dependent on model size, matching their representational alignment only for the largest evaluated models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 35 of its 59 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

35 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec

Other references · 34

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  5. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  8. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  9. 2023Sparse Autoencoders Find Highly Interpretable Features in Language Modelscited by 1,420
  10. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  11. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  12. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
22 more
  1. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  2. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 565
  3. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  4. 2023Function Vectors in Large Language Modelscited by 308
  5. 2014SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimationcited by 172
  6. 2024Compact Language Models via Pruning and Knowledge Distillationcited by 148
  7. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 127
  8. 2021Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Colorcited by 119
  9. 2024Small Language Models: Survey, Measurements, and Insightscited by 112
  10. 2020Evolution of Semantic Similarity -- A Surveycited by 83
  11. 2023Evaluating Cognitive Maps and Planning in Large Language Models with CogEvalcited by 77
  12. 2024OpenELM: An Efficient Language Model Family with Open Training and Inference Frameworkcited by 75
  13. 2022Human alignment of neural network representationscited by 74
  14. 2023INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Modelscited by 62
  15. 2020Emergence of Separable Manifolds in Deep Language Representationscited by 40
  16. 2023Instruction-tuning Aligns LLMs to the Human Braincited by 40
  17. 2023Improving neural network representations using human similarity judgmentscited by 38
  18. 2019From Clustering to Cluster Explanations via Neural Networkscited by 34
  19. 2020Building and Interpreting Deep Similarity Modelscited by 34
  20. 2024ReSi: A Comprehensive Benchmark for Representational Similarity Measurescited by 19
  21. 2020Transforming Neural Network Visual Representations to Predict Human Judgments of Similaritycited by 16
  22. 2024Explaining Text Similarity in Transformer Modelscited by 9

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Frameworkcited by 10

Similar, not cited

Close in wording, no citation either way

  1. 2024A Flexible Method for Behaviorally Measuring Alignment Between Human and Artificial Intelligence Using Representational Similarity Analysis
  2. 2025Uncovering the Computational Ingredients of Human-Like Representations in LLMs
  3. 2023Large Language Model Alignment: A Survey
  4. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
  5. 2026Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
  6. 2021A General Language Assistant as a Laboratory for Alignment
  7. 2024Uncovering Factor Level Preferences to Improve Human-Model Alignment
  8. 2024Understanding the Learning Dynamics of Alignment with Human Feedback