LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
We present LLM-BL E N D E R, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs).Our framework consists of two modules: PAIRRANKER and GEN-FUSER, addressing the observation that optimal LLMs for different examples can significantly vary.PAIRRANKER employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs.It jointly encodes the input text and a pair of candidates, using cross-attention encoders to determine the superior one.Our results demonstrate that PAIRRANKER exhibits the highest correlation with ChatGPT-based ranking.Then, GENFUSER aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses.To facilitate largescale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons.Our LLM-BL E N D E R significantly outperform individual LLMs and baseline methods across various metrics, establishing a substantial performance gap. 1 2 Open Assistant 12.61% Koala 6.71% Alpaca 11.61% Baize 11.61% StableLM 1.90% FLAN-T5 0.80% Vicuna 21.22% Dolly V2 4.50% MOSS 12.91% ChatGLM 8.51% MPT 7.61% Percentage of Examples Where Each Model Ranks First Which LLM should I use for my input?All!I can ensemble!
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
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
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
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Sagi, O., & Rokach, L. (2018) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1249 · Cited by 3,103
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
Learning to rank using gradient descent
Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., & Hullender, G. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102363 · Cited by 2,836
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Cited by
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
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Zhan, Q., Liang, Z., Ying, Z., & Kang, D. (2024) · Findings of the Association for Computational Linguistics: ACL 2024 · doi:10.18653/v1/2024.findings-acl.624 · Cited by 147
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
Chen, J., Saha, S., & Bansal, M. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.381 · Cited by 64
Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
Li, W., Lin, Y., Xia, M., & Jin, C. (2025) · arXiv · doi:10.48550/arxiv.2502.00674 · Cited by 62
Generative Artificial Intelligence in Anatomic Pathology
Brodsky, V., Ullah, E., Bychkov, A., Song, A. H., Walk, E. E., Louis, P., Rasool, G., Singh, R. S., Mahmood, F., Bui, M. M., et al. (2025) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2024-0215-ra · Cited by 48
Metadata
- Authors
- Jiang, D., Ren, X., & Lin, B. Y.
- Venue
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2023
- Pages
- 14165-14178
- OpenAlex
- W4385571189
- Cited by
- 136
- References
- 18
- FWCI
- 25.71
- 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: LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. https://app.cochat.ai/papers/10.18653/v1/2023.acl-long.792
- The paper
- Jiang, D., Ren, X., & Lin, B. Y. (2023). LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2023.acl-long.792
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.