Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Toward expert-level medical question answering with large language models
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Amin, M., Hou, L., Clark, K., Pfohl, S. R., Cole-Lewis, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03423-7 · Cited by 1,734
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Goodfellow, I. J., Mirza, M., Xiao, D., Courville, A., & Bengio, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6211 · Cited by 1,089
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2338 · Cited by 686
C-Pack: Packed Resources For General Chinese Embeddings
Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., & Nie, J.-Y. (2023) · arXiv · doi:10.48550/arxiv.2309.07597 · Cited by 514
FinGPT: Open-Source Financial Large Language Models
Yang, H., Liu, X.-Y., & Wang, C. D. (2023) · doi:10.2139/ssrn.4489826 · Cited by 475
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340
Towards Expert-Level Medical Question Answering with Large Language Models
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Hou, L., Clark, K., Pfohl, S., Cole-Lewis, H., Neal, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.09617 · Cited by 338
Cited by
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format
Akbari Gurabi, M., Nitz, L., Castravet, R.-M., Matzutt, R., Mandal, A., & Decker, S. (2026) · Lecture Notes in Computer Science · doi:10.1007/978-3-032-16092-8_27 · Cited by 3
Metadata
- Authors
- Ovadia, O., Brief, M., Mishaeli, M., & Elisha, O.
- Venue
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Published
- 2024
- Pages
- 237-250
- OpenAlex
- W4404782930
- Cited by
- 137
- References
- 16
- FWCI
- 41.68
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs. https://app.cochat.ai/papers/10.18653/v1/2024.emnlp-main.15
- The paper
- Ovadia, O., Brief, M., Mishaeli, M., & Elisha, O. (2024). Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2024.emnlp-main.15
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.