mlsanityData to 7 Oct 2026

G2: Guided Generation for Enhanced Output Diversity in LLMs

arXiv 2511.00432 ↗First posted 1 Nov 2025cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in output diversity, often generating highly similar content across multiple attempts. This limitation significantly affects tasks requiring diverse outputs, from creative writing to reasoning. Existing solutions, like temperature scaling, enhance diversity by modifying probability distributions but compromise output quality. We propose Guide-to-Generation (G2), a training-free plug-and-play method that enhances output diversity while preserving generation quality. G2 employs a base generator alongside dual Guides, which guide the generation process through decoding-based interventions to encourage more diverse outputs conditioned on the original query. Comprehensive experiments demonstrate that G2 effectively improves output diversity while maintaining an optimal balance between diversity and quality.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

27 of 47 references.

References · 27

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2020Learning to summarize from human feedbackcited by 2,562
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  6. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  7. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 671
  8. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  9. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  10. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  11. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  12. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMscited by 322
15 more
  1. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 319
  2. 2024The Effect of Sampling Temperature on Problem Solving in Large Language Modelscited by 168
  3. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 148
  4. 2025NoveltyBench: Evaluating Language Models for Humanlike Diversitycited by 64
  5. 2024Forcing Diffuse Distributions out of Language Modelscited by 48
  6. 2025Diverse Preference Optimizationcited by 48
  7. 2023Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decodingcited by 42
  8. 2024EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Samplingcited by 42
  9. 2023PREADD: Prefix-Adaptive Decoding for Controlled Text Generationcited by 29
  10. 2022Rethinking and Refining the Distinct Metriccited by 27
  11. 2024Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generationcited by 27
  12. 2024Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)cited by 23
  13. 2024Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisitioncited by 15
  14. 2024Statistical Multicriteria Benchmarking via the GSD-Frontcited by 11
  15. 2024Cross-model Control: Improving Multiple Large Language Models in One-time Trainingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamicscited by 8
  2. 2026DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writingcited by 6
  3. 2026Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Modelscited by 3
  4. 2026Where You Inject Diversity Matters: A Unified Framework for Diverse Generationcited by 2
  5. 2026The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safetycited by 1
  6. 2026Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansioncited by 1
  7. 2026Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMscited by 1
  8. 2026Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decodingcited by 1
  9. 2026GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Modelscited by 0
  10. 2026Anchorless Diversification for Parallel LLM Ideationcited by 0
  11. 2026On the Diversity of Analogy Making in Large Language Modelscited by 0
  12. 2026Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity?cited by 0
2 more
  1. 2026Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learningcited by 0
  2. 2026Improving the Diversity of LLM Outputs without a Trade-offcited by 0