In-Context Learning in Large Language Models: A Neuroscience-inspired Analysis of Representations

Safoora Yousefi, Hosein Hasanbeig, Leo Moreno Betthauser, Akanksha Saran, Raphaël Millière, Ida Momennejad

Primary Area: visualization or interpretation of learned representations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: large language models, in-context learning, representational similarity analysis

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1598