# Creative Beam Search: LLM-as-a-Judge For Improving Response Generation

arXiv: https://arxiv.org/abs/2405.00099 · HTML: https://mlsanity.com/paper/2405.00099/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [Analyzing Uncertainty in Neural Machine Translation](https://mlsanity.com/paper/1803.00047/) (2018)
- [Language GANs Falling Short](https://mlsanity.com/paper/1811.02549/) (2018)
- [Putting GPT-3's Creativity to the (Alternative Uses) Test](https://mlsanity.com/paper/2206.08932/) (2022)
- [Bits of Grass: Does GPT already know how to write like Whitman?](https://mlsanity.com/paper/2305.11064/) (2023)
- [Is AI Art Another Industrial Revolution in the Making?](https://mlsanity.com/paper/2301.05133/) (2023)

## Built on by (most cited first, 14 of 14)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [Creative Preference Optimization](https://mlsanity.com/paper/2505.14442/) (2025)
- [Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need](https://mlsanity.com/paper/2507.13966/) (2025)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [Do LLMs Agree on the Creativity Evaluation of Alternative Uses?](https://mlsanity.com/paper/2411.15560/) (2024)
- [A Transformer Based Generative Chemical Language AI Model for Structural Elucidation of Organic Compounds](https://mlsanity.com/paper/2410.14719/) (2024)
- [Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers](https://mlsanity.com/paper/2602.18292/) (2026)
- [Anchorless Diversification for Parallel LLM Ideation](https://mlsanity.com/paper/2605.30150/) (2026)
- [Typologically-Informed Candidate Reranking for LLM-based Translation into Low-Resource Languages](https://mlsanity.com/paper/2602.01162/) (2026)
- [Discovering Novel LLM Experts via Task-Capability Coevolution](https://mlsanity.com/paper/2604.14969/) (2026)
- [Playing with Words, Improving with Rewards: Training Language Models for Creative Association](https://mlsanity.com/paper/2605.27832/) (2026)
- [Coherence-Oriented Dream Scene Visualisation](https://mlsanity.com/paper/2608.05233/) (2026)
- [Recipes for Creativity: Iterative Generation and Evaluation in Large Language Models](https://mlsanity.com/paper/2608.07243/) (2026)

## Abstract (arXiv)

Large language models are revolutionizing several areas, including artificial creativity. However, the process of generation in machines profoundly diverges from that observed in humans. In particular, machine generation is characterized by a lack of intentionality and an underlying creative process. We propose a method called Creative Beam Search that uses Diverse Beam Search and LLM-as-a-Judge to perform response generation and response validation. The results of a qualitative experiment show how our approach can provide better output than standard sampling techniques. We also show that the response validation step is a necessary complement to the response generation step.