AutoRAG: Grounding text and symbols
Open accessAbstract
In safety critical domains such as the healthcare domain, systems for natural language question answering demand special correctness guarantees. Modeling problem domains formally allows for automatic transparent reasoning, but handling comprehensive formal models may quickly demand expert knowledge. Ultimately, we need a system which is as easily accessible as large language models while the correctness of its output should be checkable using trusted knowledge. Since words are ambiguous in general but concepts of a formal model are not, we propose to expand the vocabulary of a language model by concepts of a knowledge base: Motivated by retrieval-augmented generation, we introduce AutoRAG, which does not retrieve data from external sources, rather it perceives parts of the knowledge base from special vocabulary, trained by auto-encoding text and concepts. Our AutoRAG implementation for a use case in the field of nosocomial pneumonia describes concepts it associates with the input and can naturally provide a graphical depiction from the expert-made knowledge bas to allow for feasible text sanity checks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Safety applications leveraged explanations for several closely related but distinct verification goals: hallucination detection, misinformation identification, rationale verification, and atomic fact-level traceability.
“Safety applications leveraged explanations for several closely related but distinct verification goals: detecting model-generated content unsupported by the input or retrieval context ( hallucination detection ) [111]; flagging outputs that contradict authoritative medical knowledge, irrespective of whether the content was fabricated or faithfully reproduced from training data ( misinformation”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [120]
Cites
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1× · see citing works
“However, a critical chance of factually wrong but confident answers, often called hallucinations [12], remains an issue even for the latest popular LLMs [18].”
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · see citing works
Harnad, S. (1990) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(90)90087-6 · Cited by 4,235 · cited 1× · see citing works
“Given that the LM can meaningfully explain the concepts and their role in the underlying formal model, it is a solution to the symbol grounding problem [9].”
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096 · cited 1× · see citing works
“…some approaches propose to train further parameters, either as additional layers [10] or as task specific context with prefix or prompt tuning [13, 15, 40], contrasting primitive prompt engineering [16, 25, 27, 42], available for closed source LLMs. AutoRAG uses both supervised fine-tuning as…”
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
Toward expert-level medical question answering with large language models
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Amin, M., Hou, L., Clark, K., Pfohl, S. R., Cole-Lewis, H., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03423-7 · Cited by 1,734 · see citing works
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376 · see citing works
Self-Instruct: Aligning Language Models with Self-Generated Instructions
Wang, Y., Kordi, Y., Mishra, S., Liu, A., Smith, N. A., Khashabi, D., & Hajishirzi, H. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.754 · Cited by 1,243 · see citing works
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
Reynolds, L., & McDonell, K. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451760 · Cited by 952 · cited 1× · see citing works
“…as additional layers [10] or as task specific context with prefix or prompt tuning [13, 15, 40], contrasting primitive prompt engineering [16, 25, 27, 42], available for closed source LLMs. AutoRAG uses both supervised fine-tuning as well as prompt-tuning to generate task specific output,…”
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · see citing works
Almanac — Retrieval-Augmented Language Models for Clinical Medicine
Zakka, C., Shad, R., Chaurasia, A., Dalal, A. R., Kim, J. L., Moor, M., Fong, R., Phillips, C., Alexander, K., Ashley, E., et al. (2024) · NEJM AI · doi:10.1056/aioa2300068 · Cited by 424 · see citing works
REPLUG: Retrieval-augmented black-box language models
Shi, W., Min, S., Yasunaga, M., Seo, M., James, R., Lewis, M., Zettlemoyer, L., & Yih, W.-T. (2023) · arXiv · doi:10.48550/arxiv.2301.12652 · Cited by 65 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Explainability of decoder-only clinical large language models: A scoping review
Mishra, N., Abu-Hanna, A., & Calixto, I. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103501
- Authors
- Schulz, T., Luttermann, M., & Möller, R.
- Affiliations
- University of Lübeck (DE)
- German Research Centre for Artificial Intelligence (DE)
- Corresponding author
- Schulz, Tim
- Venue
- KI - Künstliche Intelligenz
- Published
- 2024-07-07
- Volume
- 38
- Issue
- 3
- Pages
- 203-217
- ISSN
- 0933-1875 (ISSN-L)
- 1610-1987
- OpenAlex
- W4400399489
- Cited by
- 4
- References
- 12
- Citations by year
- 2026: 2 · 2024: 2
- FWCI
- 0.59
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Künstliche Intell. (publishedVersion, cc-by)
- Funders
- Universität zu Lübeck
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- retrieval-augmented generation, vocabulary enrichment, nosocomial pneumonia, medical question answering, safety-critical systems
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
