{
  "id": "2310.00313",
  "version": "v1",
  "published": "2023-09-30T09:01:35.000Z",
  "updated": "2023-09-30T09:01:35.000Z",
  "title": "In-Context Learning in Large Language Models: A Neuroscience-inspired Analysis of Representations",
  "authors": [
    "Safoora Yousefi",
    "Leo Betthauser",
    "Hosein Hasanbeig",
    "Akanksha Saran",
    "Raphaël Millière",
    "Ida Momennejad"
  ],
  "categories": [
    "cs.CL"
  ],
  "abstract": "Large language models (LLMs) exhibit remarkable performance improvement through in-context learning (ICL) by leveraging task-specific examples in the input. However, the mechanisms behind this improvement remain elusive. In this work, we investigate how LLM embeddings and attention representations change following in-context-learning, and how these changes mediate improvement in behavior. We employ neuroscience-inspired techniques such as representational similarity analysis (RSA) and propose novel methods for parameterized probing and measuring ratio of attention to relevant vs. irrelevant information in Llama-2 70B and Vicuna 13B. We designed three tasks with a priori relationships among their conditions: reading comprehension, linear regression, and adversarial prompt injection. We formed hypotheses about expected similarities in task representations to investigate latent changes in embeddings and attention. Our analyses revealed a meaningful correlation between changes in both embeddings and attention representations with improvements in behavioral performance after ICL. This empirical framework empowers a nuanced understanding of how latent representations affect LLM behavior with and without ICL, offering valuable tools and insights for future research and practical applications.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-09-30T09:01:35.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "large language models",
      "in-context learning",
      "neuroscience-inspired analysis",
      "latent representations affect llm behavior",
      "attention representations"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}