The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Open accessAbstract
Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model consists of an encoder and LLM embeddings, and we propose two contrastive learning losses to train the RouterDC model. Experimental results show that RouterDC is effective in assembling LLMs and largely outperforms individual top-performing LLMs as well as existing routing methods on both in-distribution (+2.76\%) and out-of-distribution (+1.90\%) tasks. Source code is available at https://github.com/shuhao02/RouterDC.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing routing frameworks typically model this as a locally optimal decision-making problem, selecting the presumed best-fit LLM for each query individually, which overlooks global budget constraints, resulting in ineffective resource allocation.”
From OmniRouter: Budget and Performance Controllable Multi-LLM Routing (2025) · cites this paper as [5]
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.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 19
- [4][4] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, 'A simple framework for contrastive learning of visual representations,' in International Conference on Machine Learning , 2020. -
- [5][5] Z. Chen, Y. Deng, H. Yuan, K. Ji, and Q. Gu, 'Self-play fine-tuning converts weak language models to strong language models,' in International Conference on Machine Learning , 2024. -
- [12][12] N. Gupta, H. Narasimhan, W. Jitkrittum, A. S. Rawat, A. K. Menon, and S. Kumar, 'Language model cascades: Token-level uncertainty and beyond,' in International Conference on Learning Representations , 2024. -
- [15][15] P. He, X. Liu, J. Gao, and W. Chen, 'DeBERTa: Decoding-enhanced BERT with disentangled attention,' in International Conference on Learning Representations , 2021. -
- [16][16] D. Hendrycks, C. Burns, S. Basart, A. Zou, M. Mazeika, D. Song, and J. Steinhardt, 'Measuring massive multitask language understanding,' in International Conference on Learning Representations , 2021. -
- [17][17] D. Hendrycks, C. Burns, S. Kadavath, A. Arora, S. Basart, E. Tang, D. Song, and J. Steinhardt, 'Measuring mathematical problem solving with the MATH dataset,' in Neural Information Processing Systems: Datasets and Benchmarks , 2021. -
- [21][21] G. Ilharco, M. T. Ribeiro, M. Wortsman, L. Schmidt, H. Hajishirzi, and A. Farhadi, 'Editing models with task arithmetic,' in International Conference on Learning Representations , 2023. -
- [22][22] G. Izacard, M. Caron, L. Hosseini, S. Riedel, P. Bojanowski, A. Joulin, and E. Grave, 'Unsupervised dense information retrieval with contrastive learning,' Transactions on Machine Learning Research , 2022. -
- [25][25] X. Jin, X. Ren, D. Preotiuc-Pietro, and P. Cheng, 'Dataless knowledge fusion by merging weights of language models,' in International Conference on Learning Representations , 2023. -
- [26][26] S. Kullback and R. A. Leibler, 'On information and sufficiency,' The Annals of Mathematical Statistics , 1951. -
- [29][29] I. Loshchilov and F. Hutter, 'Decoupled weight decay regularization,' in International Conference on Learning Representations , 2019. -
- [32][32] J. MacQueen et al. , 'Some methods for classification and analysis of multivariate observations,' in Berkeley Symposium on Mathematical Statistics and Probability , 1967. -
- [35][35] L. Nie, Z. Ding, E. Hu, C. Jermaine, and S. Chaudhuri, 'Online cascade learning for efficient inference over streams,' in International Conference on Machine Learning , 2024. -
- [36][36] A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever, 'Learning transferable visual models from natural language supervision,' in International Conference on Machine Learning , 2021. -
- [45][45] L. Van der Maaten and G. Hinton, 'Visualizing data using t-SNE,' Journal of Machine Learning Research , 2008. -
- [47][47] H. Wang, F. M. Polo, Y. Sun, S. Kundu, E. Xing, and M. Yurochkin, 'Fusing models with complementary expertise,' in International Conference on Learning Representations , 2024. -
- [48][48] X. Wang, J. Wei, D. Schuurmans, Q. V. Le, E. H. Chi, S. Narang, A. Chowdhery, and D. Zhou, 'Selfconsistency improves chain of thought reasoning in language models,' in International Conference on Learning Representations , 2023. -
- [50][50] L. Yu, W. Jiang, H. Shi, J. Yu, Z. Liu, Y. Zhang, J. T. Kwok, Z. Li, A. Weller, and W. Liu, 'MetaMath: Bootstrap your own mathematical questions for large language models,' in International Conference on Learning Representations , 2024. -
- [51][51] M. Yue, J. Zhao, M. Zhang, L. Du, and Z. Yao, 'Large language model cascades with mixture of thought representations for cost-efficient reasoning,' in International Conference on Learning Representations , 2024. -
Cited by
Sorted by citations
Challenges in Testing Large Language Model-Based Software: A Faceted Taxonomy
Dobslaw, F., FELDT, R. H., Yoon, J., & Yoo, S. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3806396 · Cited by 21
Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing
Zhang, Y., Li, H., Chen, J., Zhang, H., Ye, P., Bai, L., & Hu, S. (2025) · International Conference on Distributed Artificial Intelligence (DAI) · doi:10.1145/3772429.3772445 · Cited by 27
Self-citationOmniRouter: Budget and Performance Controllable Multi-LLM Routing
Mei, K., Xu, W., Guo, M., Lin, S., & Zhang, Y. (2025) · arXiv · doi:10.48550/arxiv.2502.20576 · Cited by 2
Self-citationRjoub, G., Bentahar, J., Almobydeen, S. B., Pedrycz, W., & Irjoob, A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133192 · Cited by 2
Adaptive Model and Strategy Routing for Cost-Efficient LLM Services
Pan, Z., Zhang, K., Zhao, Y., & Han, Y. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792556 · Cited by 5
Metadata
- Authors
- Chen, S., Jiang, W., Lin, B., Kwok, J., & Zhang, Y.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 66305-66328
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415797314
- Cited by
- 22
- References
- 0
- Citations by year
- 2026: 19 · 2025: 3
- FWCI
- 5.32
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62076118, 62136005)
- Shenzhen Fundamental Research Program (JCYJ20210324105000003)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- dual contrastive learning, contrastive learning
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: RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models. https://app.cochat.ai/papers/10.52202/079017-2120
- The paper
- Chen, S., Jiang, W., Lin, B., Kwok, J., & Zhang, Y. (2024). RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models. Advances in Neural Information Processing Systems 37. https://doi.org/10.52202/079017-2120
