AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models
Open accessAbstract
Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains.A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling.This leads to good in-domain scores but can be impractical for domain-or resourcerestricted settings.A solution is to use a relateddomain adapter for the novel domain at test time.In this paper, we introduce Adapter-Soup, an approach that performs weight-space averaging of adapters trained on different domains.Our approach is embarrassingly parallel: first, we train a set of domain-specific adapters; then, for each novel domain, we determine which adapters should be averaged at test time.We present extensive experiments showing that AdapterSoup consistently improves performance to new domains without extra training.We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results.We explore various approaches for choosing which adapters to combine, such as text clustering and semantic similarity.We find that using clustering leads to the most competitive results on novel domains.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Several parameter merging methods have been proposed in traditional deep learning to balance optimization objectives in multi-task learning.
“In traditional deep learning, several parameter merging methods have been proposed (Wortsman et al., 2022; Chronopoulou et al., 2023; Pfeiffer et al., 2021) to balance optimization objectives in multi-task learning.”
From Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning (2026) · cites this paper as Chronopoulou et al., 2023
The Introduction and §2.3 describe AdapterSoup as a parameter-merging method: it averages the weights of adapters trained on different domains. But the paper presents it as a way to improve performance on novel domains, not as a method for balancing optimization objectives in multi-task learning. (LLM, conf=0.87)
Experimental — accuracy not yet measuredAdapter-Soups and AdapterFusion employ low-rank parameter updates.
“Adapter-Soups and AdapterFusion employ lowrank parameter updates”
From Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning (2026) · cites this paper as Chronopoulou et al., 2023
Section 2.1 describes fine-tuning adapters and averaging their weights for AdapterSoup, but does not say the updates are low-rank. A search for AdapterFusion found no passage describing that method; Section 5 instead lists adapters and LoRA layers separately. Our copy therefore does not establish the claimed property for either method. (LLM, conf=0.74)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267 · see citing works
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778 · see citing works
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · see citing works
Self-citationExploring 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 · see citing works
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741 · see citing works
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · see citing works
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684 · see citing works
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 2,523 · see citing works
Parameter-efficient transfer learning for NLP
Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Gesmundo, A., Attariyan, M., & Gelly, S. (2019) · arXiv · doi:10.48550/arxiv.1902.00751 · Cited by 2,270 · see citing works
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.740 · Cited by 2,103 · see citing works
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · Cited by 1,749 · see citing works
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Fedus, W., Zoph, B., & Shazeer, N. (2021) · arXiv · doi:10.48550/arxiv.2101.03961 · Cited by 1,005 · see citing works
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017) · arXiv · doi:10.48550/arxiv.1701.06538 · Cited by 933 · see citing works
Learning multiple visual domains with residual adapters
Rebuffi, S.-A., Bilen, H., & Vedaldi, A. (2017) · arXiv · doi:10.48550/arxiv.1705.08045 · Cited by 605 · see citing works
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer
Pfeiffer, J., Vulić, I., Gurevych, I., & Ruder, S. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.617 · Cited by 467 · see citing works
Wortsman, M., Ilharco, G., Gadre, S. Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A. S., Namkoong, H., Farhadi, A., Carmon, Y., Kornblith, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.05482 · Cited by 307 · see citing works
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
Dodge, J., Sap, M., Marasović, A., Agnew, W., Ilharco, G., Groeneveld, D., Mitchell, M., & Gardner, M. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.98 · Cited by 306 · see citing works
Self-citationSimple, Scalable Adaptation for Neural Machine Translation
Bapna, A., & Fırat, O. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1165 · Cited by 301 · see citing works
Measuring the Carbon Intensity of AI in Cloud Instances
Dodge, J., Prewitt, T., Tachet des Combes, R., Odmark, E., Schwartz, R., Strubell, E., Luccioni, A. S., Smith, N. A., DeCario, N., & Buchanan, W. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533234 · Cited by 257 · see citing works
Self-citationBranch-Train-Merge: Embarrassingly Parallel Training of Expert Language ModelsPreprint
Li, M., Gururangan, S., Dettmers, T., Lewis, M., Althoff, T., Smith, N. A., & Zettlemoyer, L. (2022) · arXiv.org · doi:10.48550/arxiv.2208.03306 · Cited by 227 · see citing works
Unsupervised Domain Clusters in Pretrained Language Models
Aharoni, R., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.692 · Cited by 181 · see citing works
Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling
Han, X., & Eisenstein, J. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1433 · Cited by 149 · see citing works
Merging Models with Fisher-Weighted Averaging
Matena, M. S., & Raffel, C. (2022) · neural information processing systems · doi:10.52202/068431-1287 · Cited by 123 · see citing works
Efficient Large Scale Language Modeling with Mixtures of Experts
Artetxe, M., Bhosale, S., Goyal, N., Mihaylov, T., Ott, M., Shleifer, S., Lin, X. V., Du, J., Iyer, S. V., Pasunuru, R., et al. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.804 · Cited by 122 · see citing works
DEMix Layers: Disentangling Domains for Modular Language Modeling
Gururangan, S., Lewis, M., Holtzman, A., Smith, N. A., & Zettlemoyer, L. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.407 · Cited by 67 · see citing works
Efficient Hierarchical Domain Adaptation for Pretrained Language Models
Chronopoulou, A., Peters, M. E., & Dodge, J. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.96 · Cited by 34 · see citing works
Self-citationEfficient Test Time Adapter Ensembling for Low-resource Language Varieties
Wang, X., Tsvetkov, Y., Ruder, S., & Neubig, G. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.63 · Cited by 23 · see citing works
Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with AdaptersPreprint
Stickland, A. C., Bérard, A., & Nikoulina, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09574 · Cited by 16 · see citing works
M2D2: A Massively Multi-Domain Language Modeling Dataset
Reid, M., Zhong, V., Gururangan, S., & Zettlemoyer, L. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.63 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, and Jian- feng Gao. 2022. Adamix: Mixture-of-adapter for parameter-efficient tuning of large language models. In Proceedings of the 2022 Conference on Empiri- cal Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates. Association for Com- putational Linguistics. 2060
- Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, and Ludwig Schmidt. 2022b. Robust fine-tuning of zero-shot models. In Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR), pages 7959-7971. Evaluation Domains Training Domain reuters techcrunch fastco nme fool inquisitr mashable tripadv. ncbi yelp Avg dailymail 17.6 23.6 24.0 21.1 23.3 18.4 23.6 39.6 20.5 44.3 25.6 wired 18.0 22.0 21.5 22.0 22.9 18.2 22.2 40.0 19.9 41.3 24.8 express 19.5 25.8 26.0 22.6 25.8 20.1 26.3 42.9 23.3 48.9 28.1 npr 20.1 25.5 25.0 27.7 23.3 20.5 23.6 42.1 21.1 42.9 27.2 librarything 19.5 24.5 24.0 24.8 23.6 19.7 24.8 38.9 21.1 39.3 26.0 instructables 20.5 25.5 25.5 25.5 24.5 20.5 25.5 40.0 21.1 41.7 27.0 entrepreneur 18.2 22.4 22.0 22.6 22.9 18.4 23.1 40.9 21.1 43.4 25.5 springer 19.7 25.0 24.5 24.5 25.3 19.9 26.8 42.9 18.4 43.8 27.1 insiderpages 23.1 28.8 29.1 32.1 25.5 23.1 27.9 37.7 23.3 35.9 28.7 ign 18.9 23.8 23.6 22.6 23.3 18.7 23.6 40.9 21.1 39.6 25.6 eventbrite 19.1 24.3 23.8 23.1 24.3 19.3 25.0 39.6 20.9 41.7 26.1 macrumors 20.3 26.0 26.3 26.3 24.5 20.9 25.5 41.3 22.4 43.4 27.7 androidheadlines 20.7 24.8 25.8 26.0 24.5 20.1 25.3 44.7 22.6 42.9 27.8 glassdoor 20.7 26.0 25.8 27.7 24.8 21.1 26.8 42.5 22.0 42.5 28.0 pcworld 18.7 22.6 22.9 23.6 23.1 18.7 23.1 42.1 21.5 42.9 25.0 csmonitor 18.9 24.0 23.8 24.0 23.6 18.9 23.8 41.3 21.5 43.4 26.3 lonelyplanet 20.7 26.0 25.8 25.0 25.3 20.7 26.6 40.4 22.6 42.9 27.6 booking 27.4 33.4 33.1 35.9 31.5 27.4 35.5 37.0 30.6 49.4 34.1 journals 21.3 26.8 26.0 27.4 26.0 21.5 28.2 46.1 18.2 46.5 28.8 frontiersin 21.1 26.8 25.5 27.7 26.0 27.7 26.0 45.6 19.3 46.5 29.2 medium 17.8 22.2 21.8 21.3 25.0 17.8 25.3 39.3 19.9 43.4 25.4 Table 7: We show the performance of each trained adapter (for the cross-domain setting) on the 10 evaluation domains. Each model has been trained for language modeling with an initial learning rate 1e -4 for 20 epochs.
Cited by
Sorted by citations
Parameter-efficient fine-tuning in large language models: a survey of methodologies
Wang, L., Chen, S., Jiang, L., Pan, S., Cai, R., Yang, S., & Yang, F. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11236-4 · Cited by 186 · see citing works
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., Chowdhury, T., Li, Y., Cui, H., Zhang, X., et al. (2025) · ACM Computing Surveys · doi:10.1145/3764579 · Cited by 263 · see citing works
Xu, L., Xie, H., Qin, S. J., Tao, X., & Wang, F. L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3657354 · Cited by 318 · see citing works
Survey of Different Large Language Model Architectures: Trends, Benchmarks, and Challenges
Shao, M., Basit, A., Karri, R., & Shafique, M. (2024) · IEEE Access · doi:10.1109/access.2024.3482107 · Cited by 110 · see citing works
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning
Poth, C., Sterz, H., Paul, I., Purkayastha, S., Engländer, L., Imhof, T., Vuli, I., Ruder, S., Gurevych, I., & Pfeiffer, J. (2023) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/2023.emnlp-demo.13 · Cited by 32 · see citing works
Pu, X., & Xu, F. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3524578 · Cited by 24 · see citing works
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications, and Opportunities
Yang, E., Shen, L., Guo, G., Wang, X., Cao, X., Zhang, J., & Tao, D. (2026) · ACM Computing Surveys · doi:10.1145/3787849 · Cited by 102 · see citing works
Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software
Ran, D., Wu, M. S., Yang, W. M., & Xie, T. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3719005 · Cited by 12 · see citing works
CAM: A cross-lingual adaptation framework for low-resource language speech recognition
Hu, Q., Zhang, Y., Zhang, X., Han, Z., & Yu, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102506 · Cited by 6 · see citing works
Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide
Szep, M., Rueckert, D., von Eisenhart‐Rothe, R., & Hinterwimmer, F. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.627 · Cited by 18 · see citing works
Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification
Sundar, A., Yang, C.-H. H., Chan, D. M., Ghosh, S., Ravichandran, V., & Nidadavolu, P. S. (2024) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw62465.2024.10627466 · Cited by 7 · see citing works
Ma, X., Xie, H., & Qin, S. J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103419 · Cited by 6 · see citing works
Language fusion via adapters for low-resource speech recognition
Hu, Q., Zhang, Y., Zhang, X., Han, Z., & Liang, X.-X. (2024) · Speech Communication · doi:10.1016/j.specom.2024.103037 · Cited by 6 · see citing works
Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies
Lawson, D., & Qureshi, A. H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610919 · Cited by 5 · see citing works
Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy
Li, T., Jiang, W., Liu, F., Huang, X., & Kwok, J. T.-Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73650-6_20 · Cited by 3 · see citing works
A Multi-modal Recipe for Improved Multi-domain Recommendation
Yi, Z., & Ounis, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88708-6_27 · Cited by 3 · see citing works
Multi-Head Adapter Routing for Cross-Task GeneralizationPreprint
Caccia, L., Ponti, E. M., Su, Z., Pereira, M., Roux, N. L., & Sordoni, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.03831 · Cited by 5 · see citing works
Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs
Heisler, M., Xing, L., Shi, G., Sadri, H., Singh, G., Zhang, W., Ye, T., Xiong, Y., Zhang, Y., & Fan, Z. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737215 · Cited by 2 · see citing works
Dam: Dynamic Adapter Merging for Continual Video QA Learning
Cheng, F., Wang, Z., Sung, Y.-L., Lin, Y.-B., Bansal, M., & Bertasius, G. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00662 · Cited by 2 · see citing works
MeLoRA : Probability measures-based low-rank adaptation with Gaussian variational inference
He, X., Geng, X., Zhang, T., Yu, M., Zhao, Y., Yang, X., Wu, M., & Yu, G. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115318 · Cited by 1 · see citing works
Improving Abstractive Summarization with Unsupervised Dynamic LoRA Mixtures
Chernyshev, D. (2024) · Lobachevskii Journal of Mathematics · doi:10.1134/s1995080224603710 · Cited by 1 · see citing works
Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning
Wu, Z., Lou, X., Ma, X., Li, Y., Liu, W., Zhang, W., Wang, J., & Zhang, Z. (2026) · arXiv · doi:10.48550/arxiv.2601.03641
Practical Tools from Domain Adaptation for Designing Inclusive, Equitable, and Robust Generative AI
Sicilia, A., & Alikhani, M. (2023) · doi:10.18653/v1/2023.ijcnlp-tutorials.3
KnowTrans: Boosting Transferability of Data Preparation LLMs via Knowledge Augmentation
Ge, Y., Li, F., Mao, Y., Yang, Y., Ge, C., Chen, Z., Long, J., & Gao, Y. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00214
A Domain-Adaptive Parameter-Efficient Fine-Tuning Method for Multi-task Learning
Liu, W., Fu, M., Cheng, S., Zhang, X., & Qu, H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-94892-3_54
Yu, H., & Yu, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4384-7_6
Continual fine-tuning with model soup for human activity recognition
Tanjung, S. Y., Yahya, B. N., & Lee, S. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02918-0
Low Rank Adaptation Enables Efficient Domain Transfer in Billion Parameter Language Models
Yang, J. (2026) · Jisuanji shenghuojia. · doi:10.54097/6w0gxa44
Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation
Ambekar, S., Hasny, M., Daza, L. A., Lang, D. M., & Schnabel, J. A. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00453
Cao, P., Yan, R., Zhao, X., Zhou, F., Zhao, W., Song, Q., & Yang, L. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3694503
A Resource-Aware Asynchronous PBT Framework with Dynamic LoRA for Heterogeneous Edge Clusters
Huang, G.-C., Huang, L.-T., & Wu, C. (2026) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge72783.2026.00037
- Authors
- Chronopoulou, A., Peters, M., Fraser, A., & Dodge, J.
- Affiliations
- Ludwig-Maximilians-Universität München (DE)
- Allen Institute for Artificial Intelligence (US)
- Munich Center for Machine Learning (DE)
- ORCID
- Peters, Matthew
- Venue
- Findings of the Association for Computational Linguistics: EACL 2023
- Published
- 2023
- Pages
- 2054-2063
- OpenAlex
- W4386566605
- Cited by
- 30
- References
- 33
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 7 · 2023: 2 · 2022: 1
- FWCI
- 5.14
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: EACL (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Open access LMU (Ludwid Maxmilian's Universitat Munchen) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- weight averaging, adapters, pre-trained language models, domain adaptation, parameter-efficient fine-tuning, test-time adaptation, domain generalization, document clustering, semantic similarity
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
