Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
December 10, 2023 Β· Declared Dead Β· π Conference on Empirical Methods in Natural Language Processing
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Oded Ovadia, Menachem Brief, Moshik Mishaeli, Oren Elisha
arXiv ID
2312.05934
Category
cs.AI: Artificial Intelligence
Cross-listed
cs.CL,
cs.LG
Citations
234
Venue
Conference on Empirical Methods in Natural Language Processing
Last Checked
3 months ago
Abstract
Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently limited, relying heavily on the characteristics of the training data. Consequently, using external datasets to incorporate new information or refine the capabilities of LLMs on previously seen information poses a significant challenge. In this study, we compare two common approaches: unsupervised fine-tuning and retrieval-augmented generation (RAG). We evaluate both approaches on a variety of knowledge-intensive tasks across different topics. Our findings reveal that while unsupervised fine-tuning offers some improvement, RAG consistently outperforms it, both for existing knowledge encountered during training and entirely new knowledge. Moreover, we find that LLMs struggle to learn new factual information through unsupervised fine-tuning, and that exposing them to numerous variations of the same fact during training could alleviate this problem.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Artificial Intelligence
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
R.I.P.
π»
Ghosted
Addressing Function Approximation Error in Actor-Critic Methods
R.I.P.
π»
Ghosted
Explanation in Artificial Intelligence: Insights from the Social Sciences
R.I.P.
π»
Ghosted
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
R.I.P.
π»
Ghosted
Complex Embeddings for Simple Link Prediction
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted