Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models

Mehrdad Farahani, Richard Johansson


Abstract
Generative language models often struggle with specialized or less-discussed knowledge. A potential solution is found in Retrieval-Augmented Generation (RAG) models which act like retrieving information before generating responses. In this study, we explore how the Atlas approach, a RAG model, decides between what it already knows (parametric) and what it retrieves (non-parametric). We use causal mediation analysis and controlled experiments to examine how internal representations influence information processing. Our findings disentangle the effects of parametric knowledge and the retrieved context. They indicate that in cases where the model can choose between both types of information (parametric and non-parametric), it relies more on the context than the parametric knowledge. Furthermore, the analysis investigates the computations involved in how the model uses the information from the context. We find that multiple mechanisms are active within the model and can be detected with mediation analysis: first, the decision of whether the context is relevant, and second, how the encoder computes output representations to support copying when relevant.
Anthology ID:
2024.emnlp-main.943
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16966–16977
Language:
URL:
https://aclanthology.org/2024.emnlp-main.943
DOI:
Bibkey:
Cite (ACL):
Mehrdad Farahani and Richard Johansson. 2024. Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16966–16977, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models (Farahani & Johansson, EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.943.pdf