# Generation Constraint Scaling Can Mitigate Hallucination

arXiv: https://arxiv.org/abs/2407.16908 · HTML: https://mlsanity.com/paper/2407.16908/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space](https://mlsanity.com/paper/2004.04092/) (2020)
- [Redefining "Hallucination" in LLMs: Towards a psychology-informed framework for mitigating misinformation](https://mlsanity.com/paper/2402.01769/) (2024)

## Built on by (most cited first, 4 of 4)

- [Position: Modular Memory is the Key to Continual Learning Agents](https://mlsanity.com/paper/2603.01761/) (2026)
- [Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?](https://mlsanity.com/paper/2503.07903/) (2025)
- [AI-Driven Climate Policy Scenario Generation for Sub-Saharan Africa](https://mlsanity.com/paper/2505.18694/) (2025)
- [A Concise Review of Hallucinations in LLMs and their Mitigation](https://mlsanity.com/paper/2512.02527/) (2025)

## Abstract (arXiv)

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit memory mechanisms. We empirically demonstrate that by simply scaling the readout vector that constrains generation in a memory-augmented LLM decoder, hallucination mitigation can be achieved in a training-free manner. Our method is geometry-inspired and outperforms a state-of-the-art LLM editing method on the task of generation of Wikipedia-like biography entries both in terms of generation quality and runtime complexity.