# Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs

arXiv: https://arxiv.org/abs/2604.06603 · HTML: https://mlsanity.com/paper/2604.06603/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://mlsanity.com/paper/2308.13259/) (2023)
- [Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval](https://mlsanity.com/paper/2410.04585/) (2024)
- [What is the Role of Small Models in the LLM Era: A Survey](https://mlsanity.com/paper/2409.06857/) (2024)
- [CRANE: Reasoning with constrained LLM generation](https://mlsanity.com/paper/2502.09061/) (2025)
- [Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts](https://mlsanity.com/paper/2405.11613/) (2024)
- [DeepEdit: Knowledge Editing as Decoding with Constraints](https://mlsanity.com/paper/2401.10471/) (2024)
- [Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling](https://mlsanity.com/paper/2504.13169/) (2025)
- [IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking](https://mlsanity.com/paper/2410.07295/) (2024)
- [KBAlign: Efficient Self Adaptation on Specific Knowledge Bases](https://mlsanity.com/paper/2411.14790/) (2024)

## Abstract (arXiv)

Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination, hindering their practical application. Though scientific theories and rules can efficiently direct the behaviors of human manipulators, LLMs still do not utilize these highly-condensed knowledge sufficiently through training or prompting. To address this issue, we propose SciDC, an LLM generation method that integrate subject-specific knowledge with strong constraints. By adopting strong LLMs to automatically convert flexible knowledge into multi-layered, standardized rules, we build an extensible framework to effectively constrain the model generation on domain tasks. Experiments on scientific tasks including industrial formulation design, clinical tumor diagnosis and retrosynthesis planning, consistently demonstrate the effectiveness of our method, achieving a 12% accuracy improvement on average compared with vanilla generation. We further discuss the potential of LLMs in automatically inductively summarizing highly-condensed knowledge, looking ahead to practical solutions for accelerating the overall scientific research process. All the code of this paper can be obtained (https://github.com/Maotian-Ma/SciDC).