Learning to Compress Prompts with Gist Tokens
Open accessThe DOI matches its OpenAlex record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally inefficient. Finetuning and distillation methods allow for specialization of LMs without prompting, but require retraining the model for each task. To avoid this trade-off entirely, we present gisting, which trains an LM to compress prompts into smaller sets of "gist" tokens which can be cached and reused for compute efficiency. Gist models can be trained with no additional cost over standard instruction finetuning by simply modifying Transformer attention masks to encourage prompt compression. On decoder (LLaMA-7B) and encoder-decoder (FLAN-T5-XXL) LMs, gisting enables up to 26x compression of prompts, resulting in up to 40% FLOPs reductions, 4.2% wall time speedups, and storage savings, all with minimal loss in output quality.
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
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
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
Transformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169
Longformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
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
Efficient transformers: A survey
Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2023) · ACM Computing Surveys · doi:10.1145/3530811 · Cited by 1,267
Efficient Transformers: A Survey
Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2020) · arXiv · doi:10.48550/arxiv.2009.06732 · Cited by 1,267
ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks
Gilardi, F., Alizadeh, M., & Kubli, M. (2023) · arXiv · doi:10.48550/arxiv.2303.15056 · Cited by 1,207
Generating Long Sequences with Sparse Transformers
Child, R., Gray, S., Radford, A., & Sutskever, I. (2019) · arXiv · doi:10.48550/arxiv.1904.10509 · Cited by 1,063
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929
Cited by
Compressing Context to Enhance Inference Efficiency of Large Language Models
Li, Y., Dong, B., Guerin, F., & Lin, C. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.391 · Cited by 253
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Jiang, H., Wu, Q., Lin, C.-Y., Yang, Y., & Qiu, L. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.825 · Cited by 168
A Survey on Large Language Model-Based Game Agents
Hu, S., Huang, T., Liu, G., Kompella, R. R., Ilhan, F., Tekin, S. F., Xu, Y., Yahn, Z., & Liu, L. (2024) · arXiv · doi:10.48550/arxiv.2404.02039 · Cited by 165
Adapting Language Models to Compress Contexts
Chevalier, A., Wettig, A., Ajith, A., & Chen, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.232 · Cited by 59
TransformerFAM: feedback attention is working memory
Hwang, D., Wang, W., Huo, Z., Sim, K. C., & Mengibar, P. M. (2024) · arXiv · doi:10.48550/arxiv.2404.09173 · Cited by 26
Metadata
- Authors
- Mu, J., Li, X. (., & Goodman, N. D.
- Venue
- neural information processing systems
- Published
- 2023-01-01
- Pages
- 19327-19352
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133221612
- Cited by
- 30
- References
- 12
- FWCI
- 5.67
- Type
- conference paper
- Language
- en
- Open access
- green
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: Learning to Compress Prompts with Gist Tokens. https://app.cochat.ai/papers/10.52202/075280-0848
- The paper
- Mu, J., Li, X. (., & Goodman, N. D. (2023). Learning to Compress Prompts with Gist Tokens. neural information processing systems. https://doi.org/10.52202/075280-0848
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.