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

• URL: http://arxiv.org/abs/2511.16540v1
• Date: Thu, 20 Nov 2025 16:53:12 GMT
• Title: Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks
• Authors: Éloïse Benito-Rodriguez, Einar Urdshals, Jasmina Nasufi, Nicky Pochinkov,
• Abstract summary: We present the first step towards a predictive framework, where the genre of a text is predicted based on its activations.<n>Using Mistral-7B and two datasets, we show that genre can be extracted with F1-scores of up to 98%.<n>Results consistently outperform the control task, providing a proof of concept that text genres can be inferred from LLMs with shallow learning models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns [50.401907401444404]
  Large language models (LLMs) are crucial for preventing misuse and building trustworthy AI systems.<n>We propose RepreGuard, an efficient statistics-based detection method.<n> Experimental results show that RepreGuard outperforms all baselines with average 94.92% AUROC on both in-distribution (ID) and OOD scenarios.
  arXiv  Detail & Related papers  (2025-08-18T17:59:15Z)
• Idiosyncrasies in Large Language Models [54.26923012617675]
  We unveil and study idiosyncrasies in Large Language Models (LLMs)<n>We find that fine-tuning text embedding models on LLM-generated texts yields excellent classification accuracy.<n>We leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies.
  arXiv  Detail & Related papers  (2025-02-17T18:59:02Z)
• LLM-based feature generation from text for interpretable machine learning [0.0]
  Existing text representations such as embeddings and bag-of-words are not suitable for rule learning due to their high dimensionality and absent or questionable feature-level interpretability.<n>This article explores whether large language models (LLMs) could address this by extracting a small number of interpretable features from text.
  arXiv  Detail & Related papers  (2024-09-11T09:29:28Z)
• A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens [20.37803751979975]
  When feeding a text into a large language model-based embedder, the obtained text embedding will be able to be aligned with the key tokens in the input text.<n>We show that this phenomenon is universal and is not affected by model architecture, training strategy, and embedding method.
  arXiv  Detail & Related papers  (2024-06-25T08:55:12Z)
• Who Wrote This? The Key to Zero-Shot LLM-Generated Text Detection Is GECScore [51.65730053591696]
  We propose a simple yet effective black-box zero-shot detection approach based on the observation that human-written texts typically contain more grammatical errors than LLM-generated texts.<n> Experimental results show that our method outperforms current state-of-the-art (SOTA) zero-shot and supervised methods.
  arXiv  Detail & Related papers  (2024-05-07T12:57:01Z)
• Token Prediction as Implicit Classification to Identify LLM-Generated Text [37.89852204279844]
  This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task. We utilize the Text-to-Text Transfer Transformer (T5) model as the backbone for our experiments.
  arXiv  Detail & Related papers  (2023-11-15T06:33:52Z)
• LLM-augmented Preference Learning from Natural Language [19.700169351688768]
  Large Language Models (LLMs) are equipped to deal with larger context lengths. LLMs can consistently outperform the SotA when the target text is large. Few-shot learning yields better performance than zero-shot learning.
  arXiv  Detail & Related papers  (2023-10-12T17:17:27Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning [104.58874584354787]
  In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
  arXiv  Detail & Related papers  (2023-01-27T18:59:01Z)
• Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
  Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
  arXiv  Detail & Related papers  (2021-10-04T08:51:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.