mlsanityData to 14 Oct 2026

Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks

arXiv 2511.16540 ↗First posted 20 Nov 2025cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Understanding Large Language Models (LLMs) is key to ensure their safe and beneficial deployment. This task is complicated by the difficulty of interpretability of LLM structures, and the inability to have all their outputs human-evaluated. In this paper, we present the first step towards a predictive framework, where the genre of a text used to prompt an LLM, is predicted based on its activations. Using Mistral-7B and two datasets, we show that genre can be extracted with F1-scores of up to 98% and 71% using scikit-learn classifiers. Across both datasets, results consistently outperform the control task, providing a proof of concept that text genres can be inferred from LLMs with shallow learning models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 20 Nov 2025.

Builds on

29 of 49 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  5. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  6. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  7. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  8. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  9. 2019Machine Unlearningcited by 1,061
  10. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  11. 2022Galactica: A Large Language Model for Sciencecited by 744
  12. 2023Towards Automated Circuit Discovery for Mechanistic Interpretabilitycited by 724
17 more
  1. 2019Designing and Interpreting Probes with Control Taskscited by 640
  2. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  3. 2023Eliciting Latent Predictions from Transformers with the Tuned Lenscited by 623
  4. 2023Language Models Represent Space and Timecited by 316
  5. 2022A Survey of Machine Unlearningcited by 312
  6. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 252
  7. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  8. 2021MoEfication: Transformer Feed-forward Layers are Mixtures of Expertscited by 152
  9. 2020Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?cited by 151
  10. 2020Metrics for Multi-Class Classification: an Overviewcited by 143
  11. 2023Modular Deep Learningcited by 83
  12. 2023Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Codingcited by 82
  13. 2023LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Codingcited by 64
  14. 2023Emergent Modularity in Pre-trained Transformerscited by 37
  15. 2023ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphscited by 27
  16. 2021From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compressioncited by 19
  17. 2023QualiGPT: GPT as an easy-to-use tool for qualitative codingcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomycited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection
  2. 2025Large Language Models For Text Classification: Case Study And Comprehensive Review
  3. 2024Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference
  4. 2024Rethinking Interpretability in the Era of Large Language Models
  5. 2025Do Large Language Models (Really) Need Statistical Foundations?
  6. 2024Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
  7. 2023Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models
  8. 2023Deep de Finetti: Recovering Topic Distributions from Large Language Models