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

• URL: http://arxiv.org/abs/2405.00099v4
• Date: Mon, 07 Oct 2024 16:45:42 GMT
• Title: Creative Beam Search: LLM-as-a-Judge For Improving Response Generation
• Authors: Giorgio Franceschelli, Mirco Musolesi,
• Abstract summary: 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.
• Score: 2.4555276449137042
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• VLM-Guided Adaptive Negative Prompting for Creative Generation [21.534474554320823]
  Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance.<n>We propose VLM-Guided Adaptive Negative-Prompting, a training-free, inference-time method that promotes creative image generation.<n>We show consistent gains in creative novelty with negligible computational overhead.
  arXiv  Detail & Related papers  (2025-10-12T17:34:59Z)
• ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection [51.93101033997245]
  Increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations.<n>We propose ThinkFake, a novel reasoning-based and generalizable framework for AI-generated image detection.<n>We show that ThinkFake outperforms state-of-the-art methods on the GenImage benchmark and demonstrates strong zero-shot generalization on the challenging LOKI benchmark.
  arXiv  Detail & Related papers  (2025-09-24T07:34:09Z)
• Jointly Reinforcing Diversity and Quality in Language Model Generations [64.72289248044514]
  Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity.<n>We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimize for response quality and semantic diversity.
  arXiv  Detail & Related papers  (2025-09-02T17:38:47Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective [65.12150411762273]
  We show that pruning random demonstrations into seemingly incoherent "gibberish" can remarkably improve performance across diverse tasks.<n>We propose a self-discover prompt optimization framework, PromptQuine, that automatically searches for the pruning strategy by itself using only low-data regimes.
  arXiv  Detail & Related papers  (2025-06-22T07:53:07Z)
• Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization [55.14484317645865]
  We develop a conditional diffusion model to produce exceptional quality prompts for offline reinforcement learning tasks. We show that the Prompt diffuser is a robust and effective tool for the prompt-tuning process, demonstrating strong performance in the meta-RL tasks.
  arXiv  Detail & Related papers  (2024-11-02T07:38:02Z)
• RISCORE: Enhancing In-Context Riddle Solving in Language Models through Context-Reconstructed Example Augmentation [1.9939549451457024]
  This paper explores how different prompting techniques impact performance on riddles that demand diverse reasoning skills. We introduce RISCORE, a fully automated prompting method that generates and utilizes contextually reconstructed sentence-based puzzles. Our experiments demonstrate that RISCORE significantly improves the performance of language models in both vertical and lateral thinking tasks.
  arXiv  Detail & Related papers  (2024-09-24T18:35:09Z)
• Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation [49.27250832754313]
  We present AgentCOT, a llm-based autonomous agent framework. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. We introduce two new strategies to enhance the performance of AgentCOT.
  arXiv  Detail & Related papers  (2024-09-19T02:20:06Z)
• Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models [3.0566617373924325]
  Sentence embedding is a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. We propose two innovative prompt engineering techniques capable of further enhancing the expressive power of PLMs' raw embeddings.
  arXiv  Detail & Related papers  (2024-04-05T07:07:15Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Towards Creativity Characterization of Generative Models via Group-based Subset Scanning [64.6217849133164]
  We propose group-based subset scanning to identify, quantify, and characterize creative processes. We find that creative samples generate larger subsets of anomalies than normal or non-creative samples across datasets.
  arXiv  Detail & Related papers  (2022-03-01T15:07:14Z)
• Towards creativity characterization of generative models via group-based subset scanning [51.84144826134919]
  We propose group-based subset scanning to quantify, detect, and characterize creative processes. Creative samples generate larger subsets of anomalies than normal or non-creative samples across datasets.
  arXiv  Detail & Related papers  (2021-04-01T14:07:49Z)
• Unsupervised Text Generation by Learning from Search [86.51619839836331]
  TGLS is a novel framework to unsupervised Text Generation by Learning. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization.
  arXiv  Detail & Related papers  (2020-07-09T04:34:48Z)
• Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks [22.585901751927995]
  We study multi-turn response generation for open-domain dialogues. In this work, we pursue a model that has a simple structure yet can effectively leverage conversation contexts for response generation.
  arXiv  Detail & Related papers  (2020-04-04T16:37:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.