Fine-tuned Language Models are Continual Learners
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions and that models trained on these instructions show strong zero-shot performance on several standard datasets.However, these models even though impressive still perform poorly on a wide range of tasks outside of their respective training and evaluation sets.To address this limitation, we argue that a model should be able to keep extending its knowledge and abilities, without forgetting previous skills.In spite of the limited success of Continual Learning we show that Fine-tuned Language Models can be continual learners.We empirically investigate the reason for this success and conclude that Continual Learning emerges from self-supervision pre-training.Our resulting model Continual-T0 (CT0) is able to learn 8 new diverse language generation tasks, while still maintaining good performance on previous tasks, spanning in total 70 datasets.Finally, we show that CT0 is able to combine instructions in ways it was never trained for, demonstrating some level of instruction compositionality.
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 2×
“In ELI5, the questions are supposed to be inquisitive, not factual like in SQuAD.”
MethodiCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · cited 1×
“External Memory methods often simply use rehearsal with a replay during training (Rebuffi et al., 2017).”
BackgroundContinual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
Catastrophic forgetting in connectionist networks
French, R. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01294-2 · Cited by 2,311
Continual Learning with Deep Generative Replay
Shin, H., Lee, J. K., Kim, J., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1705.08690 · Cited by 1,385
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101
Multitask Prompted Training Enables Zero-Shot Task Generalization
Sanh, V., Webson, A., Raffel, C., Bach, S. H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Scao, T. L., Raja, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.08207 · Cited by 612 · cited 10×
“Conversely T0 (Sanh et al., 2022) is publicly available and orders of magnitude smaller and hence we resort to working with T0.”
BackgroundMethodInfluentiale-SNLI: Natural language inference with natural language explanations
Camburu, O.-M., Rocktäschel, T., Lukasiewicz, T., & Blunsom, P. (2018) · arXiv · doi:10.48550/arxiv.1812.01193 · Cited by 367 · cited 2×
“…emotional situations using the Empathetic Dialogue data Rashkin et al. (2019); 7) Explanation Generation (Exp) where we train a model on the eSNLI (Camburu et al., 2018) benchmark to generate natural language explanations given a premise, hypothesis and a label (entail, contradict, neutral); 8)…”
Method
Cited by
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2023) · arXiv · doi:10.48550/arxiv.2307.06435 · Cited by 1,259
A Comprehensive Overview of Large Language Models
Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., & Mian, A. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3744746 · Cited by 1,257
“Concatenating fine-tuning data with a few randomly selected pre-training samples in every iteration avoids network forgetting [162], [132].”
Hassani, H., & Silva, E. S. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7020062 · Cited by 401
“It has been shown that fine-tuned language models can be continual learners, thereby giving us an indication of the future capabilities of innovations such as ChatGPT [21].”
BackgroundEnhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
Shao, Z., Gong, Y., Shen, Y., Huang, M., Duan, N., & Chen, W. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.620 · Cited by 200
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning
Luo, Y., Yang, Z., Meng, F., Li, Y., Zhou, J., & Zhang, Y. (2025) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/taslpro.2025.3606231 · Cited by 136
“Then we analyze the factors that affect the forgetting extent, such as model scales, model architectures, and general instruction tuning in Section V-B–V-E, respectively.”
Metadata
- Authors
- Scialom, T., Chakrabarty, T., & Muresan, S.
- Venue
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Published
- 2022
- Pages
- 6107-6122
- OpenAlex
- W4385573164
- Cited by
- 53
- References
- 16
- FWCI
- 7.19
- 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-tuned Language Models are Continual Learners. https://app.cochat.ai/papers/10.18653/v1/2022.emnlp-main.410
- The paper
- Scialom, T., Chakrabarty, T., & Muresan, S. (2022). Fine-tuned Language Models are Continual Learners. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2022.emnlp-main.410
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.